INDEX

Explanations

programming-related definitions and structures

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

in all caps

np_acts-logits-general · gemini-2.0-flash

technical code terms

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

↵↵

-0.94

↵

-0.91

<eos>

-0.89

-0.78

-0.77

-0.76

and

-0.73

he

-0.73

-0.70

POSITIVE LOGITS

 فريبيس

1.47

 Мексичка

1.44

Efq

1.41

ChildScrollView

1.34

 crdi

1.32

 Theſe

1.25

 الرياضيه

1.19

 يتيمه

1.18

ſelf

1.18

 Monfieur

1.18

Activations Density 0.463%

programming-related definitions and structures

in all caps

technical code terms

No Comments

No Known Activations