INDEX

Explanations

technical programming constructs and structures

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

Code, file paths, and website snippets

np_acts-logits-general · gemini-2.0-flash

code snippets and variable names

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 فريبيس

-0.55

LookAnd

-0.47

richTextPanel

-0.46

 quantities

-0.44

NamedQueries

-0.43

 propOrder

-0.43

 kaarangay

-0.40

tagHelperRunner

-0.40

 prices

-0.39

SequentialGroup

-0.39

POSITIVE LOGITS

 otomatig

0.52

IsContent

0.50

CloseOperation

0.47

TRIBUN

0.43

 ModelRenderer

0.41

 vogel

0.41

initialState

0.40

ジング

0.40

 deten

0.40

 Staff

0.40

Activations Density 0.335%

technical programming constructs and structures

Code, file paths, and website snippets

code snippets and variable names

No Comments

No Known Activations