INDEX

Explanations

specific mentions of the "New York Times"

oai_token-act-pair · gpt-3.5-turbo

mentions of "The New York Times."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

sed

-0.81

illas

-0.73

cles

-0.72

dr

-0.69

phen

-0.69

ardless

-0.68

tions

-0.67

venge

-0.67

lua

-0.66

capacity

-0.66

POSITIVE LOGITS

 Magazine

1.10

 bestselling

1.02

 Editorial

0.97

 columnist

0.89

 Digest

0.87

 editorial

0.87

 publishes

0.85

 Archive

0.85

 Publishing

0.81

Magazine

0.81

Activations Density 0.058%

specific mentions of the "New York Times"

mentions of "The New York Times."

No Comments

No Known Activations