INDEX

Explanations

criticisms and opinions about people or entities

oai_token-act-pair · gpt-3.5-turbo

expressions of criticism and evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ajo

-0.64

claimer

-0.62

ipeg

-0.60

 planes

-0.59

abiding

-0.57

CLS

-0.55

 Milky

-0.54

 Lies

-0.53

tein

-0.53

ent

-0.53

POSITIVE LOGITS

 favorably

0.85

 skept

0.83

 psychiat

0.78

maxwell

0.77

}}}

0.70

 unfairly

0.70

quet

0.69

Ú

0.69

igated

0.68

Versions

0.66

Activations Density 0.158%

criticisms and opinions about people or entities

expressions of criticism and evaluation

No Comments

No Known Activations