INDEX

Explanations

code-related keywords and structures in programming or markup languages

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

<start_of_turn>user text

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

HasColumnType

-0.43

bunal

-0.39

jus

-0.38

ecco

-0.38

writeHead

-0.37

 Starling

-0.37

Hat

-0.37

ulipas

-0.37

circ

-0.36

CodeAttribute

-0.36

POSITIVE LOGITS

Билгалдахарш

0.52

0.49

 dép

0.48

 насељу

0.48

 valentín

0.47

 wikipagina

0.46

 bağlantılar

0.46

SharedDtor

0.46

tvguidetime

0.45

 Walkover

0.44

Activations Density 0.003%

code-related keywords and structures in programming or markup languages

<start_of_turn>user text

No Comments

No Known Activations