INDEX

Explanations

statements related to Israel or Israeli people

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Israeli."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

mson

-0.95

aunder

-0.92

ocket

-0.82

owler

-0.81

luaj

-0.80

ramid

-0.80

rha

-0.79

robat

-0.79

illard

-0.77

nels

-0.75

POSITIVE LOGITS

Israeli

1.19

 Israeli

1.13

 Israelis

1.03

Palestinian

1.02

Israel

0.96

 Netanyahu

0.94

 Aviv

0.88

 Juda

0.86

 Israel

0.84

IDF

0.84

Activations Density 0.009%

statements related to Israel or Israeli people

mentions of the term "Israeli."

No Comments

No Known Activations