INDEX

Explanations

phrases related to understanding or learning something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating comprehension or acquisition of information

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥİ

-0.78

ende

-0.75

 ç¥ŀ

-0.75

ãĤµ

-0.74

Pont

-0.73

ãĥĩ

-0.73

 theorem

-0.71

ocene

-0.71

ãĤ¹

-0.71

Peace

-0.70

POSITIVE LOGITS

 Sources

0.81

 Fairfax

0.75

 Hancock

0.72

 Insider

0.72

 sources

0.72

FSA

0.71

 indications

0.70

 anecd

0.69

 PRESS

0.68

 extracts

0.68

Activations Density 0.189%

phrases related to understanding or learning something

phrases indicating comprehension or acquisition of information

No Comments

No Known Activations