INDEX

Explanations

phrases starting with "Here's what..." and similar variations

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce information or clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ename

-0.78

oit

-0.69

aukee

-0.65

ways

-0.62

rone

-0.60

idable

-0.59

lust

-0.59

 drowning

-0.58

nels

-0.57

oise

-0.57

POSITIVE LOGITS

 happened

1.13

 happens

1.13

 transpired

0.93

 else

0.90

 happ

0.89

 went

0.75

 ensued

0.75

 distinguishes

0.74

you

0.73

we

0.71

Activations Density 0.085%

phrases starting with "Here's what..." and similar variations

phrases that introduce information or clarification

No Comments

No Known Activations