INDEX

Explanations

proper nouns related to political figures and entities

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals, particularly women in leadership roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

FTWARE

-0.73

amaz

-0.70

ombat

-0.70

Sov

-0.67

ratulations

-0.65

gran

-0.65

uld

-0.64

Interstitial

-0.63

acters

-0.61

ilib

-0.61

POSITIVE LOGITS

clips

1.00

 Mock

0.79

worthy

0.74

 Reno

0.74

ials

0.72

 Janet

0.71

eers

0.70

ridge

0.70

 Carlson

0.66

bird

0.65

Activations Density 0.035%

proper nouns related to political figures and entities

mentions of specific individuals, particularly women in leadership roles

No Comments

No Known Activations