INDEX

Explanations

terms or phrases that signify something as significant or essential

oai_token-act-pair · gpt-3.5-turbo

expressions of significance or importance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

©¶æ

-0.79

artney

-0.72

uthor

-0.71

IDES

-0.70

ILA

-0.69

flat

-0.69

apons

-0.69

kered

-0.67

shirt

-0.66

çİĭ

-0.65

POSITIVE LOGITS

 factor

0.80

 milestones

0.79

 ingred

0.78

 consideration

0.78

 milestone

0.77

 considerations

0.77

 ingredient

0.76

stone

0.76

 factors

0.73

 battleground

0.70

Activations Density 0.085%

terms or phrases that signify something as significant or essential

expressions of significance or importance

No Comments

No Known Activations