INDEX

Explanations

references to a specific publication or news outlet named "Herald"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Herald" and variations of it related to news 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

perm

-0.76

entially

-0.71

ggie

-0.69

ential

-0.69

Ô

-0.67

ellen

-0.67

utm

-0.65

aeda

-0.65

riv

-0.65

olves

-0.64

POSITIVE LOGITS

 Tribune

1.14

 Herald

1.00

 Examiner

0.83

ry

0.76

Typ

0.73

 Chronicle

0.71

 Gazette

0.70

zeb

0.69

 Globe

0.68

 Newsp

0.67

Activations Density 0.011%

references to a specific publication or news outlet named "Herald"

instances of the word "Herald" and variations of it related to news articles

No Comments

No Known Activations