INDEX

Explanations

explanations or clarifications in text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "explained."

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

inal

-0.80

illet

-0.76

 ILCS

-0.71

engeance

-0.70

venge

-0.69

pired

-0.69

vernment

-0.69

 contracted

-0.66

otion

-0.66

ascus

-0.65

POSITIVE LOGITS

 explains

1.01

why

0.95

WHY

0.90

 explained

0.87

 explain

0.83

ĸļ

0.83

 explaining

0.82

WER

0.82

 explanations

0.81

 Explain

0.80

Activations Density 0.017%

explanations or clarifications in text

instances of the word "explained."

No Comments

No Known Activations