INDEX

Explanations

references to artifact identifiers in dependency code snippets

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

XML dependency 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

so

-0.35

off

-0.35

 isolated

-0.35

 tower

-0.34

 last

-0.34

 spot

-0.34

 norm

-0.33

lot

-0.33

 relative

-0.33

pit

-0.32

POSITIVE LOGITS

 defaultstate

3.64

IContainer

2.61

+#+#

2.39

 StatefulWidget

2.08

WebControls

1.81

oredCriteria

1.76

SequentialGroup

1.28

 initComponents

1.12

 AssemblyCulture

1.11

addCriterion

1.09

Activations Density 0.001%

references to artifact identifiers in dependency code snippets

XML dependency tags

No Comments

No Known Activations