INDEX

Explanations

the word "excuse" and related terms

oai_token-act-pair · gpt-3.5-turbo

instances of the word "excuse" and its variations 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

yss

-0.95

acid

-0.91

itals

-0.87

duino

-0.85

jri

-0.82

semble

-0.77

iegel

-0.75

weeney

-0.75

ibaba

-0.75

utenberg

-0.74

POSITIVE LOGITS

 excuse

1.14

 excuses

1.10

 explanations

0.85

WHY

0.77

why

0.76

 justification

0.75

 explanation

0.74

 justifying

0.72

åĳ

0.71

 inaction

0.70

Activations Density 0.025%

the word "excuse" and related terms

instances of the word "excuse" and its variations in various contexts

No Known Activations