INDEX

Explanations

phrases indicating a summary or conclusion

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize the concept of "inclusion."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

hower

-0.68

gaard

-0.67

 Citation

-0.66

 offending

-0.64

sworth

-0.61

fell

-0.58

Ö¼

-0.58

oru

-0.58

bidden

-0.57

deen

-0.57

POSITIVE LOGITS

clusive

1.03

 vain

0.76

 moderation

0.75

clus

0.73

offensive

0.72

 sudden

0.72

CLUS

0.71

effic

0.69

 favor

0.65

 goodness

0.64

Activations Density 0.049%

phrases indicating a summary or conclusion

phrases that emphasize the concept of "inclusion."

No Comments

No Known Activations