INDEX

Explanations

information or events that have been reported or mentioned by a source

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "reportedly."

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

ĸļ

-0.82

etime

-0.76

ERAL

-0.75

bern

-0.74

Appearances

-0.71

gers

-0.69

alist

-0.68

ravel

-0.65

allas

-0.65

ender

-0.65

POSITIVE LOGITS

 entertained

0.85

 instructed

0.79

 obtained

0.78

 proc

0.77

 possessed

0.76

 disposed

0.76

 purchased

0.75

 solic

0.75

 overheard

0.74

 suffered

0.73

Activations Density 0.035%

information or events that have been reported or mentioned by a source

occurrences of the word "reportedly."

No Comments

No Known Activations