INDEX

Explanations

words related to international relations and political events, particularly involving the United States

oai_token-act-pair · gpt-3.5-turbo

references to the United States and its actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Virt

-0.77

 Dickinson

-0.74

ãĥ£

-0.68

ersion

-0.67

andra

-0.66

iott

-0.64

 brakes

-0.63

 TAMADRA

-0.62

 Cassidy

-0.60

xes

-0.60

POSITIVE LOGITS

taboola

0.98

division

0.81

webkit

0.80

_-

0.78

san

0.78

hap

0.77

alien

0.77

entimes

0.77

based

0.76

themed

0.76

Activations Density 0.010%

words related to international relations and political events, particularly involving the United States

references to the United States and its actions

No Comments

No Known Activations