INDEX

Explanations

instances of the name "Richard" with varying degrees of importance or relevance

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Richard."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ascript

-0.78

sites

-0.75

ihar

-0.73

mercial

-0.70

TOR

-0.69

awaru

-0.68

icago

-0.67

 Pradesh

-0.65

cedented

-0.65

worn

-0.65

POSITIVE LOGITS

 Dawkins

0.90

 Richard

0.90

 Wallace

0.86

 Pryor

0.85

 Spencer

0.82

 Johnson

0.81

 Nixon

0.81

 Strauss

0.79

 Abraham

0.79

 Roberts

0.77

Activations Density 0.010%

instances of the name "Richard" with varying degrees of importance or relevance

mentions of the name "Richard."

No Comments

No Known Activations