INDEX

Explanations

political terms and party names

oai_token-act-pair · gpt-3.5-turbo

references to political parties and their affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

rawdownloadcloneembedreportprint

-0.76

 airspace

-0.74

holes

-0.73

ashington

-0.72

 holes

-0.69

ĸļ

-0.67

 overload

-0.67

 exhibitions

-0.65

 sightings

-0.64

 attribution

-0.64

POSITIVE LOGITS

 Liberals

1.18

 centrist

1.18

 Syri

1.18

 coalition

1.14

 party

1.14

 Socialist

1.14

 Conservatives

1.13

 Party

1.11

 Liberal

1.11

 faction

1.10

Activations Density 0.310%

political terms and party names

references to political parties and their affiliations

No Comments

No Known Activations