INDEX

Explanations

assignments and definitions in programming or markup contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

—

-0.80

 nonatomic

-0.77

 Duran

-0.75

 Tutu

-0.74

awtextra

-0.72

±

-0.72

ContextCompat

-0.72

–

-0.71

 Pust

-0.70

POSITIVE LOGITS

0.94

 Romains

0.90

 tremp

0.89

)]=

0.89

 doré

0.87

 Inscrivez

0.84

 piú

0.84

0.83

 malade

0.83

 fédé

0.83

Activations Density 0.251%

assignments and definitions in programming or markup contexts

No Comments

No Known Activations