INDEX

Explanations

elements related to programming constructs and structures

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

Code snippets and programming-related text

np_acts-logits-general · gemini-2.0-flash

code snippets, programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MemoryWarning

-0.50

 AssemblyVersion

-0.46

 ostavi

-0.44

toolStripButton

-0.43

ſelf

-0.42

EnableWeb

-0.40

 ſes

-0.39

Personendaten

-0.39

TypedDataSet

-0.39

 leſs

-0.38

POSITIVE LOGITS

if

0.57

-------------</

0.53

 surla

0.48

 Infórmanos

0.46

switch

0.45

PerformLayout

0.44

//

0.44

 CreateTagHelper

0.42

Certain

0.42

int

0.42

Activations Density 0.228%

elements related to programming constructs and structures

Code snippets and programming-related text

code snippets, programming constructs

No Comments

No Known Activations