INDEX

Explanations

words related to medical conditions, specifically HIV/AIDS

oai_token-act-pair · gpt-3.5-turbo

references to demographics and statistics related to social issues

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

 Collider

-0.61

 Tornado

-0.57

ciation

-0.56

 explan

-0.54

 steroids

-0.53

 Vortex

-0.52

 sunset

-0.52

 fundament

-0.51

 Execution

-0.51

ifice

-0.50

POSITIVE LOGITS

 whom

0.84

who

0.76

selves

0.73

united

0.64

 backgrounds

0.63

EStream

0.62

 pets

0.60

amate

0.60

irs

0.60

heastern

0.59

Activations Density 1.542%

words related to medical conditions, specifically HIV/AIDS

references to demographics and statistics related to social issues

No Comments

No Known Activations