INDEX

Explanations

mentions of the name "Lewinsky"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Lew" in various contexts

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

ACTED

-0.87

OPLE

-0.78

 vain

-0.76

 à¨

-0.72

Republic

-0.68

Companies

-0.67

senal

-0.65

CHR

-0.64

Ø§ÙĦ

-0.63

company

-0.63

POSITIVE LOGITS

andowski

1.31

Lew

1.11

insky

0.91

Lew

0.91

ington

0.89

itsch

0.87

sey

0.87

enstein

0.82

etz

0.81

erk

0.80

Activations Density 0.007%

mentions of the name "Lewinsky"

mentions of the name "Lew" in various contexts

No Comments

No Known Activations