INDEX

Explanations

programming language syntax and structure

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

ьаж

-0.36

 bulunabilir

-0.32

ResId

-0.31

 exposed

-0.31

hit

-0.30

 admitted

-0.30

berapa

-0.28

₩

-0.27

 ويكيپيديا

-0.27

 ब्रेकडाउन

-0.27

POSITIVE LOGITS

GEBURTS

0.64

 noDo

0.63

AndroidJUnit

0.63

OGND

0.61

adaptiveStyles

0.59

extAlignment

0.59

caux

0.58

exitRule

0.57

tvguidetime

0.57

ChildScrollView

0.56

Activations Density 0.003%

programming language syntax and structure

No Comments

No Known Activations