INDEX

Explanations

proper nouns of individuals

oai_token-act-pair · gpt-3.5-turbo

proper names, specifically individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 âĢº

-0.77

 ......

-0.67

 ..........

-0.65

_-_

-0.59

ãĥ©ãĥ³

-0.57

âĢİ

-0.56

arial

-0.56

 ï¿½

-0.55

Reloaded

-0.54

.............

-0.53

POSITIVE LOGITS

owan

0.55

ensibly

0.53

ritical

0.52

reth

0.51

 vetoed

0.50

 muse

0.49

addafi

0.47

illus

0.46

mun

0.46

ussion

0.46

Activations Density 0.974%

proper nouns of individuals

proper names, specifically individuals

No Comments

No Known Activations