INDEX

Explanations

key programming terms and concepts

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

colon, no

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 surla

-0.53

 يتيمه

-0.47

 وتسجيلات

-0.44

ніципалі

-0.42

 للاسماء

-0.39

ientôt

-0.38

guien

-0.36

 صوتيه

-0.35

Notae

-0.35

 whoſe

-0.33

POSITIVE LOGITS

SharedCtor

0.65

 otomatig

0.48

########.

0.47

cedure

0.46

}{@

0.45

 démocr

0.44

UnknownFieldSet

0.44

ResumeLayout

0.43

 Lauder

0.43

FieldBuilder

0.43

Activations Density 0.016%

key programming terms and concepts

colon, no

No Comments

No Known Activations