INDEX

Explanations

references to articles within a text

oai_token-act-pair · gpt-3.5-turbo

the mention of articles, indicating discussions about various topics or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

creen

-0.86

cffff

-0.84

elsius

-0.78

pter

-0.74

cffffcc

-0.73

inav

-0.72

ey

-0.72

gettable

-0.71

²¾

-0.69

 palate

-0.67

POSITIVE LOGITS

 articles

0.96

 article

0.93

meal

0.87

 Articles

0.76

 ARTICLE

0.76

 published

0.75

RFC

0.75

 essays

0.72

hook

0.72

marks

0.70

Activations Density 0.025%

references to articles within a text

the mention of articles, indicating discussions about various topics or subjects

No Comments

No Known Activations