INDEX

Explanations

proper nouns, mostly names of people and organizations

oai_token-act-pair · gpt-3.5-turbo

specific names and terms associated with individuals and organizations in a scientific and news context

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

natureconservancy

-0.68

olina

-0.63

ccording

-0.58

zona

-0.56

pred

-0.55

 guiActiveUnfocused

-0.54

matically

-0.54

ãĤ¿

-0.53

IUM

-0.53

AMI

-0.53

POSITIVE LOGITS

tein

0.84

owship

0.58

ruary

0.56

heit

0.56

aux

0.56

Chr

0.52

beard

0.52

 wool

0.51

 Sierra

0.51

steen

0.50

Activations Density 1.069%

proper nouns, mostly names of people and organizations

specific names and terms associated with individuals and organizations in a scientific and news context

No Comments

No Known Activations