INDEX

Explanations

references to annotated sections or metadata in a structured document

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

documentation comments with @tags

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

setVerticalGroup

-0.59

parsedMessage

-0.53

didSet

-0.50

webElementXpaths

-0.50

MessageOf

-0.50

RenderAtEndOf

-0.49

enterOuterAlt

-0.48

 BoxFit

-0.48

SharedDtor

-0.47

basicConfig

-0.47

POSITIVE LOGITS

ngdoc

0.44

EventQueue

0.42

')->

0.40

peur

0.40

uParam

0.39

➞

0.38

')).

0.38

("$.

0.37

}`).

0.36

frog

0.36

Activations Density 0.008%

references to annotated sections or metadata in a structured document

documentation comments with @tags

No Comments

No Known Activations