INDEX

Explanations

references to a specific person named Stuart

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Stuart."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

uscript

-0.90

enic

-0.89

nect

-0.88

mental

-0.86

inki

-0.84

nexus

-0.83

alach

-0.82

stery

-0.82

externalActionCode

-0.81

aic

-0.80

POSITIVE LOGITS

 Pearce

1.08

 Keane

0.94

 Buckingham

0.93

 Williams

0.87

 Sterling

0.86

 Waters

0.86

 Giles

0.86

 Farage

0.84

 Stuart

0.83

 Ellis

0.83

Activations Density 0.113%

references to a specific person named Stuart

mentions of the name "Stuart."

No Comments

No Known Activations