INDEX

Explanations

the name "Netanyahu" as a proper noun

oai_token-act-pair · gpt-3.5-turbo

mentions of Benjamin Netanyahu

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

teenth

-0.87

 Pyth

-0.85

Reviewer

-0.84

itialized

-0.77

anwhile

-0.76

ively

-0.76

ĸļ

-0.72

orative

-0.70

ibles

-0.68

ebin

-0.68

POSITIVE LOGITS

anyahu

1.21

 Netanyahu

1.05

 ministerial

0.88

 Jinping

0.82

anca

0.81

stein

0.79

etz

0.78

 bloc

0.76

itz

0.74

 Aviv

0.73

Activations Density 0.010%

the name "Netanyahu" as a proper noun

mentions of Benjamin Netanyahu

No Comments

No Known Activations