INDEX

Explanations

references to layout and user interface components in code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

awtextra

-0.56

'},

-0.55

endphp

-0.53

GeoNames

-0.52

 strconv

-0.51

maten

-0.50

ünkü

-0.50

basicConfig

-0.50

tvguidetime

-0.49

bbean

-0.49

POSITIVE LOGITS

IndentedString

0.66

webElementXpaths

0.66

expandindo

0.59

клопе

0.59

Cyfeiriadau

0.57

 Lightboxes

0.56

انگلیسی

0.56

 חיצוניים

0.55

felf

0.54

 Roskov

0.53

Activations Density 0.237%

references to layout and user interface components in code

No Comments

No Known Activations