INDEX

Explanations

references to testing frameworks and functions in code

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

t(...) or t

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

maris

-0.42

ReusableCell

-0.42

tagHelper

-0.42

tvguidetime

-0.40

attr

-0.40

 sceptre

-0.39

 umano

-0.39

WEBPACK

-0.39

 blob

-0.39

'@/

-0.38

POSITIVE LOGITS

InitVars

0.57

 disambiguazione

0.50

хьтан

0.50

 defaultstate

0.49

IntoConstraints

0.48

 gynhyrchwyd

0.47

AutoScaleMode

0.46

hoeddwyd

0.46

Diwedd

0.46

IndentedString

0.45

Activations Density 0.100%

references to testing frameworks and functions in code

t(...) or t

No Comments

No Known Activations