INDEX

Explanations

Java imports and utility classes

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

kloped

-0.63

 mold

-0.61

DotNetBar

-0.61

 Fannie

-0.59

Mold

-0.58

mold

-0.58

elstein

-0.57

هة

-0.56

occupe

-0.56

("^

-0.56

POSITIVE LOGITS

util

1.33

 util

0.94

Util

0.94

AxisAlignment

0.85

 الاطلاع

0.84

 Мексичка

0.73

 Util

0.72

yntaxException

0.71

jsoup

0.69

utile

0.68

Activations Density 0.026%

Java imports and utility classes

No Comments

No Known Activations