INDEX

Explanations

words related to articles or written text

oai_token-act-pair · gpt-3.5-turbo

the end of document markers

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

Not in Any Lists

No Comments

Negative Logits

emale

-0.68

ilaterally

-0.65

Interstitial

-0.64

stood

-0.59

akespe

-0.59

 horizont

-0.58

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.56

xxxx

-0.56

itud

-0.55

 helicop

-0.55

POSITIVE LOGITS

zbollah

0.64

UTERS

0.63

chwitz

0.60

Â¶

0.57

Elsa

0.57

 largeDownload

0.57

Wiki

0.55

 Mant

0.54

ANS

0.54

Pos

0.54

Activations Density 0.226%

words related to articles or written text

the end of document markers

No Comments

No Known Activations