INDEX

Explanations

patterns of symbols arranged in a systematic format

oai_token-act-pair · gpt-3.5-turbo

symbols representing bullet points or lists

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

è»

-0.64

interstitial

-0.58

çļ

-0.57

greg

-0.56

ç¥ŀ

-0.55

bryce

-0.55

Ã¶n

-0.54

bnb

-0.54

hedral

-0.52

enhagen

-0.52

POSITIVE LOGITS

 Niet

0.60

 timed

0.55

 exped

0.53

 urgency

0.52

asel

0.52

 seconds

0.48

ip

0.48

 POST

0.48

 elic

0.47

Activations Density 1.853%

patterns of symbols arranged in a systematic format

symbols representing bullet points or lists

No Comments

No Known Activations