INDEX

Explanations

proper nouns typically containing the letter 'L' followed by 's'

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'L' or its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 mathemat

-0.85

 proble

-0.66

 Palestin

-0.65

 rotating

-0.62

 presumed

-0.62

 fortun

-0.61

 scattering

-0.60

 scrut

-0.60

 cryst

-0.60

 phosphorus

-0.59

POSITIVE LOGITS

1.00

ï¸ı

0.95

ship

0.92

TION

0.81

ski

0.78

inson

0.77

tyard

0.73

ved

0.73

tracks

0.73

Ã±a

0.72

Activations Density 0.197%

proper nouns typically containing the letter 'L' followed by 's'

instances of the letter 'L' or its variations

No Comments

No Known Activations