INDEX

Explanations

words that have specific meanings, particularly names, in various languages

oai_token-act-pair · gpt-3.5-turbo

phrases that define or explain the meaning of words or names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

olicy

-0.77

vable

-0.75

zanne

-0.74

udic

-0.71

iments

-0.71

aeper

-0.71

emort

-0.71

 Vaugh

-0.70

abases

-0.69

ADS

-0.68

POSITIVE LOGITS

literally

1.00

meaning

0.86

 Dwell

0.86

 Beautiful

0.77

God

0.76

 Literally

0.76

 Meaning

0.74

 Fool

0.73

selves

0.72

 Divine

0.71

Activations Density 0.131%

words that have specific meanings, particularly names, in various languages

phrases that define or explain the meaning of words or names

No Comments

No Known Activations