INDEX

Explanations

political figures and their actions

oai_token-act-pair · gpt-3.5-turbo

names of political figures 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

Roberts

-1.13

 Robertson

-1.12

ATI

-0.92

 Manziel

-0.89

 Arpaio

-0.87

 Barnett

-0.84

 Carbuncle

-0.83

 Bundy

-0.83

 Rangers

-0.82

 Griffin

-0.80

POSITIVE LOGITS

 Schumer

1.01

umenthal

0.93

 Dianne

0.91

 Vermont

0.89

 Blumenthal

0.83

 Minority

0.82

 Stamford

0.82

 Feinstein

0.80

democratic

0.79

 Democrat

0.79

Activations Density 0.214%

political figures and their actions

names of political figures and their affiliations

No Comments

No Known Activations