INDEX

Explanations

mentions of generated code

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

start of user turn

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

writeFieldEnd

-0.69

ніципалі

-0.69



-0.64

ViewImports

-0.61

 jsPsych

-0.61

 Paglinawan

-0.61

 ब्रेकडाउन

-0.60

titleMargin

-0.60

jsxFileName

-0.58

 FetchType

-0.58

POSITIVE LOGITS

CodeAttribute

0.40

mtable

0.37

entlichen

0.35

 defaultstate

0.31

 CURIAM

0.31

ℏ

0.30

maßen

0.30

zuführen

0.30

 مشين

0.29

 uppgifter

0.29

Activations Density 0.000%

mentions of generated code

start of user turn

No Comments

No Known Activations