INDEX

Explanations

references to specific individuals and titles

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

 itſelf

-0.47

 öff

-0.46

 です

-0.45

Подробнее

-0.44

 này

-0.44

-0.43

 kemudian

-0.43

Complete

-0.43

ksikon

-0.43

 czasem

-0.43

POSITIVE LOGITS

PhysRev

1.01

SourceChecksum

0.75

 ProtoMessage

0.74

ReusableCell

0.72

########.

0.71

 Paglinawan

0.70

'{@

0.69

 doInBackground

0.68

TagMode

0.67

'])){

0.66

Activations Density 0.983%

references to specific individuals and titles

No Comments

No Known Activations