INDEX

Explanations

phrases indicating a lack of deviation or exceptionalism

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a comparison or highlight differences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Milky

-0.69

Pax

-0.66

 Advisory

-0.61

DA

-0.60

 periodic

-0.60

 Bots

-0.60

 Hitch

-0.59

 Supplemental

-0.59

 Moder

-0.59

OK

-0.57

POSITIVE LOGITS

 whatsoever

1.00

nor

0.77

Transform

0.72

interstitial

0.71

UFC

0.71

etheless

0.70

bleacher

0.70

aunt

0.70

nor

0.69

tes

0.68

Activations Density 0.048%

phrases indicating a lack of deviation or exceptionalism

phrases that indicate a comparison or highlight differences

No Comments

No Known Activations