INDEX

Explanations

numerical representations and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 ModelExpression

-1.00

tagHelperRunner

-0.98

 disambiguazione

-0.94

IsMutable

-0.86

IsContent

-0.85

таратура

-0.82

 Administrativna

-0.81

InstrumentedTest

-0.80

webElementXpaths

-0.80

:✨

-0.79

POSITIVE LOGITS

بوابة

0.49

 الأس

0.48

ker

0.45

mer

0.44

 strtok

0.44

tan

0.43

واب

0.42

свя

0.42

 कार

0.41

Activations Density 0.371%

numerical representations and symbols

No Comments

No Known Activations