INDEX

Explanations

programming constructs related to thread management in code

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

Code snippets/programming-related text

np_acts-logits-general · gemini-2.0-flash

programming language constructs

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

ارد

-0.46

寸

-0.41

мя

-0.41

ItemLayout

-0.40

 Witness

-0.40

 виде

-0.38

 witness

-0.37

tem

-0.37

<eos>

-0.37

POSITIVE LOGITS

 autorytatywna

0.89

 beginnetje

0.88

 NDEBUG

0.82

Архівовано

0.81

клопе

0.79

DockStyle

0.78

ScopeManager

0.77

 CreateTagHelper

0.77

AnchorStyles

0.76

GEBURTSDATUM

0.75

Activations Density 0.024%

programming constructs related to thread management in code

Code snippets/programming-related text

programming language constructs

No Comments

No Known Activations