INDEX

Explanations

command phrases prompting action or engagement

oai_token-act-pair · gpt-3.5-turbo

phrases that initiate or encourage further exploration or engagement with content

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

ulton

-0.76

CONCLUS

-0.75

LOD

-0.73

ãĥĨãĤ£

-0.73

 suscept

-0.70

Untitled

-0.70

EStreamFrame

-0.68

cffffcc

-0.65

SAY

-0.65

NetMessage

-0.61

POSITIVE LOGITS

mate

0.98

points

0.95

boxes

0.95

lists

0.94

hee

0.92

ers

0.91

list

0.90

etts

0.87

enhagen

0.82

LIST

0.82

Activations Density 0.018%

command phrases prompting action or engagement

phrases that initiate or encourage further exploration or engagement with content

No Comments

No Known Activations