INDEX

Explanations

phrases indicating the application of rules, laws, or concepts

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "applies to."

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

ovych

-0.74

fast

-0.69

ileaks

-0.63

;;;;;;;;

-0.63

 SERV

-0.62

lund

-0.62

 Accessed

-0.59

icer

-0.59

SourceFile

-0.59

Champ

-0.59

POSITIVE LOGITS

pless

0.95

 practise

0.78

 encompass

0.77

 determine

0.73

 mainland

0.69

 coincide

0.69

iling

0.68

 compensate

0.67

 behalf

0.67

gans

0.67

Activations Density 0.128%

phrases indicating the application of rules, laws, or concepts

instances of the phrase "applies to."

No Comments

No Known Activations