INDEX

Explanations

phrases related to public opinion and reactions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating public sentiment or audience reactions

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

tein

-0.83

 ministerial

-0.76

 patents

-0.75

 skirt

-0.72

 successor

-0.70

HQ

-0.70

 srfAttach

-0.69

 master

-0.67

chapter

-0.66

Chain

-0.65

POSITIVE LOGITS

 clam

1.03

ustomed

0.82

 cheering

0.80

 overwhelmingly

0.80

 hungry

0.76

anx

0.76

 understandably

0.75

 cheers

0.75

raged

0.73

selves

0.73

Activations Density 0.623%

phrases related to public opinion and reactions

phrases indicating public sentiment or audience reactions

No Comments

No Known Activations