INDEX

Explanations

negative statements, specifically those with 'not' or 'did not'

oai_token-act-pair · gpt-3.5-turbo

phrases indicating negation or the absence of something

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

 horizont

-0.68

 proportions

-0.68

)=(

-0.66

 Levels

-0.63

tons

-0.61

Isn

-0.61

you

-0.60

 Gems

-0.60

ERG

-0.60

Tank

-0.59

POSITIVE LOGITS

 officially

1.08

 formally

1.01

 explicitly

0.97

 necessarily

0.97

 publicly

0.95

 definitively

0.93

 confir

0.90

icably

0.90

 exactly

0.82

 disclose

0.82

Activations Density 0.243%

negative statements, specifically those with 'not' or 'did not'

phrases indicating negation or the absence of something

No Comments

No Known Activations