INDEX

Explanations

elements related to data processing or manipulation in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

ValueStyle

-0.70

("$.

-0.58

ссер

-0.58

oa̍t

-0.56

argout

-0.55

 Wirth

-0.55

ỡng

-0.54

 IndexPath

-0.54

########.

-0.53

UserScript

-0.53

POSITIVE LOGITS

fromCharCode

0.84

Normdaten

0.59

NOPQRST

0.57

charCodeAt

0.55

teclado

0.51

unicode

0.51

 AssemblyCulture

0.50

 characters

0.49

 ISNI

0.49

endfor

0.48

Activations Density 1.419%

elements related to data processing or manipulation in programming

No Comments

No Known Activations