INDEX

Explanations

mentions of political leaders

oai_token-act-pair · gpt-3.5-turbo

references to political leaders

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

Pwr

-0.73

rawdownloadcloneembedreportprint

-0.65

urious

-0.64

ITNESS

-0.64

schild

-0.63

urses

-0.63

crew

-0.62

agon

-0.62

azaki

-0.61

ensable

-0.60

POSITIVE LOGITS

esses

0.93

doms

0.92

boards

0.86

 emer

0.78

ess

0.75

pieces

0.74

aroo

0.72

pins

0.72

stration

0.72

board

0.71

Activations Density 0.030%

mentions of political leaders

references to political leaders

No Comments

No Known Activations