INDEX

Explanations

mentions of a specific individual on Twitter

oai_token-act-pair · gpt-3.5-turbo

mentions of Donald J. Trump and his name variations

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

halla

-0.73

iffin

-0.69

earchers

-0.68

ength

-0.66

inav

-0.65

bnb

-0.64

ngth

-0.63

ativity

-0.61

pora

-0.60

rious

-0.58

POSITIVE LOGITS

å£«

0.87

merce

0.85

ourt

0.74

administ

0.66

Ð´

0.65

lich

0.64

Î½

0.64

×ª

0.64

insk

0.63

venth

0.62

Activations Density 0.279%

mentions of a specific individual on Twitter

mentions of Donald J. Trump and his name variations

No Comments

No Known Activations