INDEX

Explanations

references to political identification categories, particularly "independents."

oai_token-act-pair · gpt-3.5-turbo

references to political affiliations, specifically independents and moderates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

advertising

-0.69

ttp

-0.69

itual

-0.67

 Sciences

-0.64

Detailed

-0.64

thur

-0.63

fare

-0.63

iton

-0.63

Liv

-0.62

NING

-0.62

POSITIVE LOGITS

 independents

1.19

 strugg

0.96

ecided

0.84

 centr

0.73

 outsider

0.73

 republic

0.71

 overflow

0.70

 peel

0.69

rats

0.69

 minded

0.68

Activations Density 0.016%

references to political identification categories, particularly "independents."

references to political affiliations, specifically independents and moderates

No Comments

No Known Activations