INDEX

Explanations

block structures or defined segments in code

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

Code snippets and hexadecimal values

np_acts-logits-general · gemini-2.0-flash

code or numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

 محفوظة

-0.57

dafx

-0.57

TypedDataSet

-0.56

Personendaten

-0.54

notation

-0.54

DeleteBehavior

-0.54

WriteBarrier

-0.54

annica

-0.53

 مرئيه

-0.51

LVANIA

-0.51

POSITIVE LOGITS

uxxxx

0.43

\}\\

0.42

 ......

0.40

↵↵↵↵

0.39

······

0.39

 orgánica

0.37

↵↵↵↵↵↵

0.37

......

0.37

<code>

0.36

Activations Density 0.467%

block structures or defined segments in code

Code snippets and hexadecimal values

code or numbers

No Comments

No Known Activations