INDEX

Explanations

terms related to data processing and manipulation in programming contexts

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

matched vs unmatched cases and controls

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 nakalista

-0.50

Showing

-0.44

IconModule

-0.43

 بلد

-0.42

 nahilalakip

-0.40

 Showing

-0.39

Демографія

-0.39

rativa

-0.39

 lenker

-0.38

 circulaire

-0.38

POSITIVE LOGITS

 NSCoder

0.52

transQ

0.45

jgl

0.44

 betweenstory

0.42

 bekannt

0.41

CodedInputStream

0.41

featureID

0.40

 passent

0.40

rophes

0.39

GeneratedMessage

0.39

Activations Density 0.029%

terms related to data processing and manipulation in programming contexts

matched vs unmatched cases and controls

No Comments

No Known Activations