INDEX

Explanations

phrases related to novel concepts or new initiatives

oai_token-act-pair · gpt-3.5-turbo

instances of the word "idea."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Ago

-0.74

ndum

-0.72

 Peaks

-0.66

lake

-0.66

 ILCS

-0.65

eworthy

-0.63

gar

-0.60

east

-0.60

 Reporting

-0.59

lee

-0.59

POSITIVE LOGITS

ually

1.08

 idea

0.82

atical

0.81

 moot

0.81

yout

0.78

@#&

0.73

atics

0.73

uitive

0.73

SourceFile

0.71

ual

0.70

Activations Density 0.030%

phrases related to novel concepts or new initiatives

instances of the word "idea."

No Comments

No Known Activations