INDEX

Explanations

phrases expressing admiration or surprise

oai_token-act-pair · gpt-3.5-turbo

phrases expressing strong opinions or reactions about various subjects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é¾įå¥ĳå£«

-0.77

 Â¶

-0.72

 Oswald

-0.67

-0.65

 ILCS

-0.65

CI

-0.62

 Entered

-0.61

\<

-0.61

 Freddie

-0.61

=~

-0.59

POSITIVE LOGITS

 coincidence

1.01

ils

0.97

uras

0.86

 wonderful

0.86

lot

0.84

 bunch

0.81

 lovely

0.81

 terrific

0.79

 marvelous

0.78

 fantastic

0.78

Activations Density 0.032%

phrases expressing admiration or surprise

phrases expressing strong opinions or reactions about various subjects

No Comments

No Known Activations