INDEX

Explanations

quantitative measurements expressed as rates or quantities per unit of time or other units

oai_token-act-pair · gpt-3.5-turbo

metrics and measurements related to time intervals and quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

actionDate

-0.85

ĪĴ

-0.72

reth

-0.70

tymology

-0.69

atorial

-0.69

 Roose

-0.68

 Jonas

-0.66

gotten

-0.66

uador

-0.65

enhagen

-0.64

POSITIVE LOGITS

 thereafter

0.85

 increments

0.81

 basis

0.78

Â²

0.73

 average

0.71

 throughout

0.69

(~

0.68

 allowance

0.68

Footnote

0.67

 plus

0.67

Activations Density 0.041%

quantitative measurements expressed as rates or quantities per unit of time or other units

metrics and measurements related to time intervals and quantities

No Comments

No Known Activations