INDEX

Explanations

commonalities between two entities or individuals

oai_token-act-pair · gpt-3.5-turbo

instances of the word "both" to indicate shared experiences or actions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Trend

-0.89

ugu

-0.81

fecture

-0.76

vernment

-0.76

antics

-0.74

plete

-0.71

renheit

-0.70

ournal

-0.69

esis

-0.68

uran

-0.68

POSITIVE LOGITS

 sides

1.31

 halves

1.30

 sexes

1.24

 genders

1.01

 thirds

0.87

ocating

0.83

 ends

0.82

 sets

0.81

 coasts

0.81

 parties

0.73

Activations Density 0.042%

commonalities between two entities or individuals

instances of the word "both" to indicate shared experiences or actions

No Comments

No Known Activations