INDEX

Explanations

references to different presidents named George

oai_token-act-pair · gpt-3.5-turbo

mentions of individuals named George, particularly former presidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

nir

-0.83

 crawl

-0.83

lain

-0.79

Reviewed

-0.77

places

-0.77

pmwiki

-0.77

mble

-0.73

unal

-0.72

shapeshifter

-0.72

âķ

-0.71

POSITIVE LOGITS

 Soros

0.92

 Orwell

0.91

 Bush

0.91

 Wallace

0.88

 Zimmerman

0.88

 Lucas

0.86

 Whites

0.83

Clo

0.80

 Quin

0.79

 Kenn

0.79

Activations Density 0.010%

references to different presidents named George

mentions of individuals named George, particularly former presidents

No Comments

No Known Activations