INDEX

Explanations

references to literary works and authors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 AssemblyCulture

-0.73

expandindo

-0.61

StructEnd

-0.61

enseignements

-0.59

alakip

-0.59

 unknownFields

-0.56

:✨

-0.56

 للمعارف

-0.56

genodigd

-0.56

 pembun

-0.54

POSITIVE LOGITS

co

0.32

awaiter

0.32

 seminal

0.32

art

0.31

 avatar

0.29

における

0.29

 poster

0.29

we

0.29

$/,

0.28

Die

0.28

Activations Density 0.057%

references to literary works and authors

No Comments

No Known Activations