INDEX

Explanations

references to media information such as news sources and social media accounts

oai_token-act-pair · gpt-3.5-turbo

various punctuation marks and formatting indicators suggesting visual content or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

©¶æ

-0.66

maxwell

-0.61

geries

-0.61

 Classics

-0.60

eln

-0.60

xual

-0.58

Ard

-0.58

 Petra

-0.57

 retiring

-0.56

 Rolls

-0.56

POSITIVE LOGITS

ÂłÂłÂłÂł

0.90

Introduced

0.81

Original

0.78

Advertisements

0.76

Previously

0.75

RELATED

0.74

Letter

0.74

________________________________________________________________

0.73

Madison

0.73

ONSORED

0.73

Activations Density 0.179%

references to media information such as news sources and social media accounts

various punctuation marks and formatting indicators suggesting visual content or emphasis

No Comments

No Known Activations