INDEX

Explanations

references to or mentions of the country "Israel."

oai_token-act-pair · gpt-3.5-turbo

mentions of the country Israel

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-0.84

nant

-0.77

geoning

-0.77

mson

-0.77

luaj

-0.71

rencies

-0.71

 Jackets

-0.71

robat

-0.69

urations

-0.68

utic

-0.68

POSITIVE LOGITS

 Aviv

0.88

ites

0.87

anyahu

0.86

Israel

0.86

aretz

0.81

 Israel

0.81

apolis

0.79

ifa

0.76

 Juda

0.75

 Netanyahu

0.74

Activations Density 0.025%

references to or mentions of the country "Israel."

mentions of the country Israel

No Comments

No Known Activations