INDEX

Explanations

occurrences of the word "bill" with varying degrees of relevance

oai_token-act-pair · gpt-3.5-turbo

references to the word "bill."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 confir

-0.78

 lightsaber

-0.77

herry

-0.74

 referen

-0.73

 slippery

-0.73

 apprentice

-0.72

uper

-0.68

 caution

-0.67

yrinth

-0.66

 vigilance

-0.66

POSITIVE LOGITS

bill

1.25

iard

1.25

boards

0.92

jamin

0.92

BILL

0.91

 Maher

0.91

Bill

0.88

 Cosby

0.83

agos

0.79

ions

0.78

Activations Density 0.003%

occurrences of the word "bill" with varying degrees of relevance

references to the word "bill."

No Comments

No Known Activations