INDEX

Explanations

mentions of social media platforms and activities like posting, scrolling, and tweeting

oai_token-act-pair · gpt-3.5-turbo

tweets and social media interactions

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

 elector

-0.67

 Hezbollah

-0.66

 deterrence

-0.62

 damages

-0.62

-0.59

 Shiite

-0.58

 destabil

-0.57

 impunity

-0.57

 arsen

-0.56

POSITIVE LOGITS

nesday

0.95

 myself

0.94

 haha

0.88

 blogging

0.86

:)

0.78

my

0.76

igslist

0.73

 ðŁĻĤ

0.72

:-)

0.69

;)

0.67

Activations Density 2.132%

mentions of social media platforms and activities like posting, scrolling, and tweeting

tweets and social media interactions

No Comments

No Known Activations