INDEX

Explanations

phrases related to specific technical terms and proper nouns

oai_token-act-pair · gpt-3.5-turbo

specific proper nouns and terms related to activities and organizational elements

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

ht

-0.57

Merit

-0.54

tera

-0.51

gpu

-0.51

terness

-0.49

uner

-0.49

 diplom

-0.48

acle

-0.48

acas

-0.47

Thy

-0.46

POSITIVE LOGITS

 tradem

0.58

etheless

0.57

 constitu

0.56

 Citiz

0.55

galitarian

0.53

orno

0.52

vertis

0.50

entity

0.50

Discussion

0.50

Maps

0.49

Activations Density 1.258%

phrases related to specific technical terms and proper nouns

specific proper nouns and terms related to activities and organizational elements

No Comments

No Known Activations