INDEX

Explanations

words related to pharmaceuticals and medications

oai_token-act-pair · gpt-3.5-turbo

terms related to drugs and gaming products

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

Ô

-0.74

 Friend

-0.64

Berry

-0.62

ãĤ¢ãĥ«

-0.61

azeera

-0.61

ãĥŃ

-0.61

 Vill

-0.60

\\\\\\\\

-0.59

ãĤ·ãĥ£

-0.59

Ĭ±

-0.59

POSITIVE LOGITS

 itself

1.07

's

0.77

washer

0.72

osphere

0.72

 himself

0.72

 outright

0.71

iverse

0.70

wright

0.68

 beforehand

0.67

 Gutenberg

0.65

Activations Density 0.484%

words related to pharmaceuticals and medications

terms related to drugs and gaming products

No Comments

No Known Activations