INDEX

Explanations

words related to Israel

oai_token-act-pair · gpt-3.5-turbo

mentions of Israel

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mson

-0.85

geoning

-0.81

ĸļ

-0.79

nant

-0.79

urations

-0.79

Discussion

-0.74

adeon

-0.73

tm

-0.72

utic

-0.68

aunder

-0.67

POSITIVE LOGITS

Israel

0.92

 Aviv

0.89

anyahu

0.88

ites

0.86

 Israel

0.85

aretz

0.81

 Juda

0.76

Israeli

0.76

 Israelis

0.74

apolis

0.74

Activations Density 0.020%

words related to Israel

mentions of Israel

No Comments

No Known Activations