INDEX

Explanations

programming syntax and structure related to algorithm implementation

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

Code or special characters

np_acts-logits-general · gemini-2.0-flash

programming operators and keywords

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

↵

-0.48

«

-0.42

</em>

-0.41

↵↵

-0.40

por

-0.40

šech

-0.39

«

-0.38

„

-0.38

 skin

-0.38

 Additional

-0.37

POSITIVE LOGITS

 GenerationType

1.05

:✨

0.87

ArgsConstructor

0.86

BeginContext

0.78

ViewFeatures

0.78

 насељу

0.78

expandindo

0.76

 HasFactory

0.76

 AssemblyTitle

0.75

ArrowToggle

0.72

Activations Density 0.211%

programming syntax and structure related to algorithm implementation

Code or special characters

programming operators and keywords

No Comments

No Known Activations