INDEX

Explanations

programming language constructs, particularly related to volatile memory and function definitions

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

Code or assembly language snippets

np_acts-logits-general · gemini-2.0-flash

programming, cpuid, system calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

UnknownFields

-0.74

Datuak

-0.68

expandindo

-0.63

DockStyle

-0.57

 Wiktionnaire

-0.55

 refined

-0.55

DebuggerStep

-0.54

<",

-0.54

Izvori

-0.53

Jegyzetek

-0.52

POSITIVE LOGITS

✨:

0.57

InjectAttribute

0.53

PRWEB

0.53

 الحره

0.52

icionar

0.51

UGAL

0.49

exels

0.49

таратура

0.49

 INVENTION

0.48

 Paglinawan

0.48

Activations Density 0.074%

programming language constructs, particularly related to volatile memory and function definitions

Code or assembly language snippets

programming, cpuid, system calls

No Comments

No Known Activations