INDEX

Explanations

proper nouns related to specific individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals, particularly focusing on the names Gross and Foley

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

ronic

-0.84

ade

-0.83

oke

-0.83

illion

-0.79

AIN

-0.78

encies

-0.77

ersed

-0.75

role

-0.75

rolled

-0.74

oct

-0.73

POSITIVE LOGITS

Vie

0.74

xit

0.70

 guiName

0.69

 contrad

0.68

vig

0.66

 Parish

0.65

espie

0.63

©¶æ

0.62

 Confederacy

0.61

 Tone

0.60

Activations Density 0.046%

proper nouns related to specific individuals

mentions of specific individuals, particularly focusing on the names Gross and Foley

No Comments

No Known Activations