INDEX

Explanations

references to websites and social media platforms

oai_token-act-pair · gpt-3.5-turbo

references to authorship and attribution in articles

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

gow

-0.59

gui

-0.57

pex

-0.56

gew

-0.55

phas

-0.54

iage

-0.53

stood

-0.53

Args

-0.53

stones

-0.52

lication

-0.52

POSITIVE LOGITS

 subscribe

0.77

Subscribe

0.77

 newsletter

0.76

 HuffPost

0.76

iframe

0.74

 Email

0.74

 Subscribe

0.73

 Newsletter

0.72

 embed

0.72

 Huffington

0.71

Activations Density 0.987%

references to websites and social media platforms

references to authorship and attribution in articles

No Comments

No Known Activations