INDEX

Explanations

phrases indicating a long period of time or continuity

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "long" in reference to duration or time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Correction

-0.72

 dstg

-0.68

 Thumbnails

-0.67

Obj

-0.65

 Compass

-0.65

externalActionCode

-0.63

 Bucket

-0.63

 GOODMAN

-0.62

 Safety

-0.62

 Warden

-0.62

POSITIVE LOGITS

itud

1.26

ago

1.17

been

0.93

 awaited

0.92

entimes

0.90

 resisted

0.89

 been

0.88

 advocated

0.87

 overdue

0.87

 championed

0.86

Activations Density 0.038%

phrases indicating a long period of time or continuity

the repeated use of the word "long" in reference to duration or time

No Comments

No Known Activations