INDEX

Explanations

the word "a" at various activation levels

oai_token-act-pair · gpt-3.5-turbo

instances of the article "a"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

anism

-0.67

inel

-0.67

Enter

-0.67

livious

-0.65

AIDS

-0.63

tain

-0.63

independent

-0.63

ahu

-0.63

 Recep

-0.60

ielding

-0.60

POSITIVE LOGITS

lot

1.95

LOT

1.64

 bunch

1.61

 couple

1.39

ton

1.32

few

1.27

 pretty

1.27

 HUGE

1.25

 whole

1.20

 nice

1.18

Activations Density 0.465%

the word "a" at various activation levels

instances of the article "a"

No Comments

No Known Activations