INDEX

Explanations

words related to voting or expressing a choice

oai_token-act-pair · gpt-3.5-turbo

references to voting and electoral actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

fal

-0.72

ology

-0.70

ptoms

-0.68

OLOGY

-0.65

xia

-0.64

clair

-0.64

ĸļ

-0.62

ologies

-0.62

iasis

-0.62

ebin

-0.62

POSITIVE LOGITS

 unanimously

1.09

 overwhelmingly

0.95

YES

0.94

 against

0.92

 decisively

0.87

yes

0.86

 accordingly

0.78

 differently

0.77

 approving

0.77

 enthusiastically

0.74

Activations Density 0.053%

words related to voting or expressing a choice

references to voting and electoral actions

No Comments

No Known Activations