INDEX

Explanations

code structure elements and their associated methods or functions

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

command execution

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

 <>",

-0.36

RenderAtEndOf

-0.36

ypeł

-0.33

PLICATE

-0.31

APORE

-0.31

disposing

-0.31

UnsafeEnabled

-0.31

 negatives

-0.31

reszcie

-0.31

aarrggbb

-0.30

POSITIVE LOGITS

 CURIAM

0.57

ariConfig

0.52

ovico

0.52

Dni

0.49

 Organis

0.49

Izvori

0.47

Buku

0.47

pædia

0.47

Identyfik

0.47

рядок

0.44

Activations Density 0.023%

code structure elements and their associated methods or functions

command execution

No Comments

No Known Activations