INDEX

Explanations

references to the terrorist organization Al-Qaeda

oai_token-act-pair · gpt-3.5-turbo

references to the organization Al-Qaeda

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

 Gron

-0.90

 Seah

-0.84

 Wald

-0.77

 Hubble

-0.74

ðĿ

-0.74

WD

-0.72

 Brun

-0.71

 Marvel

-0.71

 Goodell

-0.71

Veh

-0.71

POSITIVE LOGITS

aeda

1.01

 affiliates

0.97

istani

0.96

 terrorists

0.95

 insurgents

0.91

 bombings

0.90

 affiliated

0.88

 affiliate

0.87

 operatives

0.87

Qaeda

0.86

Activations Density 0.019%

references to the terrorist organization Al-Qaeda

references to the organization Al-Qaeda

No Comments

No Known Activations