INDEX

Explanations

phrases related to specific places or locations, especially those associated with significance or importance

oai_token-act-pair · gpt-3.5-turbo

phrases indicating significant places or moments in time

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

ramids

-0.71

 ItemLevel

-0.70

 Canaver

-0.69

 externalToEVAOnly

-0.67

 Hayden

-0.66

alties

-0.66

 sqor

-0.65

iaries

-0.64

bryce

-0.64

 Bened

-0.64

POSITIVE LOGITS

 luck

0.89

 reckoning

0.85

 sorts

0.79

 contention

0.78

 origin

0.77

 shame

0.70

 ours

0.69

 honour

0.68

 yours

0.68

 misfortune

0.68

Activations Density 0.240%

phrases related to specific places or locations, especially those associated with significance or importance

phrases indicating significant places or moments in time

No Comments

No Known Activations