INDEX

Explanations

instances of the word "before"

oai_token-act-pair · gpt-3.5-turbo

references to prior occurrences or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

erville

-0.62

 equivalent

-0.59

atana

-0.58

 cones

-0.56

urther

-0.55

ãĥ¼ãĥ

-0.54

utenberg

-0.53

arov

-0.52

equal

-0.52

BAT

-0.52

POSITIVE LOGITS

0.74

0.73

 committing

0.70

 settling

0.69

ebin

0.67

isner

0.66

mort

0.66

hand

0.65

 donating

0.64

 realizing

0.62

Activations Density 0.077%

instances of the word "before"

references to prior occurrences or experiences

No Comments

No Known Activations