INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

verbs in the past tense

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

arta

-1.00

OUNT

-0.81

DNA

-0.75

Solution

-0.73

fitting

-0.73

 srfAttach

-0.72

Det

-0.72

ajo

-0.71

Effective

-0.70

Handle

-0.70

POSITIVE LOGITS

vironment

0.72

river

0.69

eer

0.67

nergy

0.65

utenant

0.64

berman

0.63

 uranium

0.63

gall

0.63

doms

0.62

ppelin

0.62

Activations Density 0.014%

proper nouns

verbs in the past tense

No Known Activations