INDEX

Explanations

positive or high numerical values within a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

aarrggbb

-0.58

elemField

-0.57

 wagen

-0.51

Rifer

-0.50

 contextLoads

-0.50

رشف

-0.49

Sabato

-0.49

Коммента

-0.49

 Lago

-0.49

 Lenti

-0.49

POSITIVE LOGITS

onActivityResult

0.58

etc

0.56

Kanpo

0.55

endfor

0.53

 <=",

0.53

MethodImpl

0.52

}`}>

0.51

ifrance

0.50

достатки

0.50

 FetchType

0.49

Activations Density 0.170%

positive or high numerical values within a technical context

No Comments

No Known Activations