INDEX

Explanations

references to numerical data or statistical measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

Bakgrunnsstoff

-0.45

 للاسماء

-0.45

setScene

-0.44

addGap

-0.42

 iconLine

-0.42

NameInMap

-0.41

 snippetHide

-0.41

setOnAction

-0.39

 generating

-0.39

mybatisplus

-0.39

POSITIVE LOGITS

 cdti

0.44

Personendaten

0.43

Reasons

0.42

reasons

0.41

thma

0.40

 Reasons

0.40

 MainAxisSize

0.39

 reasons

0.39

fara

0.39

 Colonies

0.39

Activations Density 0.239%

references to numerical data or statistical measures

No Comments

No Known Activations