INDEX

Explanations

mentions of the mainstream media

oai_token-act-pair · gpt-3.5-turbo

references to media bias or criticism of media reporting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

elfth

-0.74

 Payments

-0.71

 Transform

-0.68

 GitHub

-0.68

apeshifter

-0.67

 Reserv

-0.66

 Engineers

-0.66

 Conservation

-0.65

 Alto

-0.64

 Rebellion

-0.64

POSITIVE LOGITS

 sensational

1.21

 coverage

1.18

reporting

1.16

 portraying

1.13

 portray

1.11

 reporting

1.08

 Coverage

1.07

 pundits

1.03

 outlets

1.02

 Reporting

1.01

Activations Density 0.448%

mentions of the mainstream media

references to media bias or criticism of media reporting

No Comments

No Known Activations