INDEX

Explanations

phrases related to actions or events occurring

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

vich

-0.68

rand

-0.65

 Citation

-0.63

iam

-0.62

HAM

-0.60

 MÃ©

-0.60

 Adren

-0.60

eur

-0.60

 Badge

-0.59

thood

-0.58

POSITIVE LOGITS

 forefront

1.17

 conclusion

1.11

 realization

1.00

 knees

0.98

 doorstep

0.97

 fruition

0.97

 shores

0.96

 fray

0.95

 fold

0.89

 rescue

0.85

Activations Density 0.130%

phrases related to actions or events occurring

occurrences of the word "the"

No Comments

No Known Activations