INDEX

Explanations

references to the geographical location "Palestine."

oai_token-act-pair · gpt-3.5-turbo

references to Palestine

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

 gust

-0.80

inarily

-0.79

rive

-0.78

gling

-0.77

unders

-0.76

edo

-0.72

lev

-0.70

ripp

-0.70

asio

-0.70

lasses

-0.70

POSITIVE LOGITS

 Liberation

1.01

 Palestine

0.94

 Territories

0.92

 Refugees

0.91

lehem

0.86

estine

0.84

 Authority

0.79

adr

0.75

 Arabs

0.74

adelphia

0.73

Activations Density 0.011%

references to the geographical location "Palestine."

references to Palestine

No Comments

No Known Activations