INDEX

Explanations

news and information-related terms or topics

oai_token-act-pair · gpt-3.5-turbo

references to news stories and their significance

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

ependence

-0.80

emale

-0.78

gger

-0.77

gee

-0.77

 acquaintance

-0.76

othal

-0.74

ajor

-0.74

alus

-0.73

ggie

-0.73

cki

-0.73

POSITIVE LOGITS

Article

0.93

 trending

0.87

Content

0.86

article

0.85

Interstitial

0.78

 headlines

0.78

 alerts

0.75

Trend

0.74

 Stories

0.74

 Torrent

0.73

Activations Density 0.028%

news and information-related terms or topics

references to news stories and their significance

No Comments

No Known Activations