INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of people, companies, and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

)=(

-0.64

 Titanic

-0.64

DPR

-0.57

 silence

-0.56

 Underworld

-0.56

 needles

-0.55

 inconsistency

-0.55

 Comet

-0.54

 root

-0.54

 Rebellion

-0.54

POSITIVE LOGITS

eworks

1.03

isine

0.94

isons

0.86

anche

0.86

omm

0.81

arel

0.81

inton

0.79

ernels

0.78

aches

0.77

ules

0.77

Activations Density 0.411%

proper nouns

proper nouns, particularly names of people, companies, and organizations

No Comments

No Known Activations