INDEX

Explanations

structured data representations, possibly related to tree or graph structures in programming

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-0.81

StructEnd

-0.73

AddTagHelper

-0.62

 }}"></

-0.59

==""){

-0.59

 {}));

-0.58

 createSlice

-0.58

 Autorisations

-0.56

ABASE

-0.55

帖最后由

-0.55

POSITIVE LOGITS

picasso

0.58

 colectiva

0.54

 Universitaria

0.54

inaires

0.53

 Exteriores

0.53

 مواليد

0.52

՝

0.52

 popoli

0.52

 hooves

0.51

 munka

0.49

Activations Density 0.004%

structured data representations, possibly related to tree or graph structures in programming

No Comments

No Known Activations