INDEX

Explanations

references to the name "Osama Bin Laden."

oai_token-act-pair · gpt-3.5-turbo

references to Osama bin Laden

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

GRE

-0.69

ISS

-0.69

Premium

-0.68

WD

-0.66

 Constantin

-0.65

Tokens

-0.65

 Patreon

-0.64

Lex

-0.64

 VMware

-0.64

PASS

-0.64

POSITIVE LOGITS

 Laden

1.05

abad

0.97

 Jinping

0.92

ghan

0.83

agascar

0.79

addafi

0.79

 Battalion

0.79

selage

0.77

doms

0.77

 Hussein

0.76

Activations Density 0.017%

references to the name "Osama Bin Laden."

references to Osama bin Laden

No Comments

No Known Activations