INDEX

Explanations

details related to instructions or steps

oai_token-act-pair · gpt-3.5-turbo

references to tasks, actions, or requirements that involve effort or productivity

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

Dear

-0.47

abetes

-0.43

cigarettes

-0.43

 dstg

-0.43

DCS

-0.43

Joined

-0.41

cca

-0.41

 è£ıç

-0.40

 Somebody

-0.40

Enlarge

-0.40

POSITIVE LOGITS

 however

1.04

 meanwhile

0.91

 therefore

0.80

 moreover

0.79

anwhile

0.73

 though

0.72

 furthermore

0.71

 additionally

0.58

 also

0.56

 thus

0.54

Activations Density 2.637%

details related to instructions or steps

references to tasks, actions, or requirements that involve effort or productivity

No Comments

No Known Activations