INDEX

Explanations

references to specific geographic locations - in this case, the mention of locations related to the Israeli-Palestinian conflict

oai_token-act-pair · gpt-3.5-turbo

references to the term "Israeli" in various contexts related to conflict and military actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

-1.03

aunder

-0.99

mble

-0.85

ĸļ

-0.83

utic

-0.82

ramid

-0.81

rencies

-0.78

orsche

-0.78

iddler

-0.77

hematic

-0.77

POSITIVE LOGITS

 Israeli

0.98

Israeli

0.95

 Israelis

0.94

apolis

0.86

 embassy

0.86

Palestinian

0.85

 Netanyahu

0.82

 Jews

0.82

 Aviv

0.81

Israel

0.81

Activations Density 0.016%

references to specific geographic locations - in this case, the mention of locations related to the Israeli-Palestinian conflict

references to the term "Israeli" in various contexts related to conflict and military actions

No Comments

No Known Activations