INDEX

Explanations

versions and file formats in technical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

featureID

-0.80

ftc

-0.61

 HasFactory

-0.60

()?;

-0.60

AccessorTable

-0.59

 ModelRenderer

-0.58

TagMode

-0.57

########.

-0.57

ⓧ

-0.56

GEBURTSDATUM

-0.56

POSITIVE LOGITS

 vectorielles

0.64

jaciół

0.60

 mosso

0.59

 scattata

0.55

 metropolitana

0.53

phazard

0.53

 néz

0.52

 arabe

0.52

 Italijanski

0.52

 contemporaine

0.52

Activations Density 0.172%

versions and file formats in technical documentation

No Comments

No Known Activations