INDEX

Explanations

references to various entities or subjects such as "Lion King", "Spider-Man", or "Gotham" that evoke specific pop culture or fictional elements

oai_token-act-pair · gpt-3.5-turbo

suffixes that indicate a specific form of nouns or adjectives

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lain

-0.81

lished

-0.77

ÄŁ

-0.72

 prepar

-0.71

ANCE

-0.70

Interstitial

-0.69

Effective

-0.66

ãĥ¼ãĥ³

-0.66

 completion

-0.65

 elapsed

-0.65

POSITIVE LOGITS

 Squid

0.97

fish

0.85

hawk

0.80

boy

0.75

hawks

0.74

Squ

0.72

 Ogre

0.71

 squid

0.71

beard

0.71

cube

0.69

Activations Density 0.325%

references to various entities or subjects such as "Lion King", "Spider-Man", or "Gotham" that evoke specific pop culture or fictional elements

suffixes that indicate a specific form of nouns or adjectives

No Comments

No Known Activations