INDEX

Explanations

relationships or associations between concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Мексичка

-0.61

magyar

-0.58

uty

-0.57

 uſed

-0.57

__':

-0.56

 oprot

-0.55

Efq

-0.55

الصفحه

-0.55

 Conſ

-0.55

liferay

-0.55

POSITIVE LOGITS

interopRequire

0.54

 versus

0.53

 Versus

0.51

 아니라

0.46

 whether

0.46

 else

0.46

 ModelExpression

0.45

IndentedString

0.45

RepeatedField

0.44

 rather

0.43

Activations Density 0.431%

relationships or associations between concepts

No Comments

No Known Activations