INDEX

Explanations

programming constructs and syntax elements in code

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

code configuration and relations

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

 papal

-0.40

 Papal

-0.39

seros

-0.38

InjectAttribute

-0.36

dil

-0.34

ngdoc

-0.34

sle

-0.34

 lich

-0.33

DebuggerNonUser

-0.33

Autoritní

-0.33

POSITIVE LOGITS

 nonUne

0.56

Microkernel

0.56

 resourceCulture

0.56

hilangan

0.54

rungsseite

0.53

Rhestr

0.51

 balení

0.49

 GoogleFonts

0.49

 esquecer

0.48

 gdyby

0.47

Activations Density 0.001%

programming constructs and syntax elements in code

code configuration and relations

No Comments

No Known Activations