INDEX

Explanations

statements calling for action or expressing a strong opinion

oai_token-act-pair · gpt-3.5-turbo

the phrase "should be" and its variations

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

Wid

-0.81

 Wick

-0.71

urrence

-0.63

plex

-0.63

Fra

-0.62

 Bomber

-0.60

 Ripple

-0.59

ãĤ¼ãĤ¦ãĤ¹

-0.59

Pix

-0.59

Or

-0.59

POSITIVE LOGITS

fitting

1.09

 able

1.04

 judged

1.02

 ashamed

0.97

 avoided

0.96

 treated

0.95

 regarded

0.94

 kept

0.93

 applauded

0.93

ige

0.89

Activations Density 0.089%

statements calling for action or expressing a strong opinion

the phrase "should be" and its variations

No Comments

No Known Activations