INDEX

Explanations

political content, including mentions of government actions and policies

oai_token-act-pair · gpt-3.5-turbo

phrases related to political accountability and criticism

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

/-

-0.78

Republic

-0.68

atos

-0.68

%%

-0.67

Storage

-0.66

LTD

-0.66

mination

-0.65

 ILCS

-0.65

)/

-0.64

orm

-0.63

POSITIVE LOGITS

his

0.87

 populism

0.86

 apologized

0.85

 acknowledging

0.85

 tweeting

0.85

 aides

0.84

 Huckabee

0.81

he

0.79

 flanked

0.79

piv

0.79

Activations Density 0.856%

political content, including mentions of government actions and policies

phrases related to political accountability and criticism

No Comments

No Known Activations