INDEX

Explanations

references to programming concepts and structures

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

Tokens after variable names or symbols

np_acts-logits-general · gemini-2.0-flash

repeated integer types

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

<eos>

-0.52

<",

-0.49

].

-0.49

\",

-0.47

 municipalité

-0.47

/,

-0.46

mmation

-0.46

>,

-0.46

 históricos

-0.45

 inéd

-0.45

POSITIVE LOGITS

 चीज़ों

0.74

########.

0.74

 nahilalakip

0.72

ⓧ

0.69

DoubleQuotes

0.67

原始内容存档于

0.67

MockBean

0.67

Obrázky

0.66

nestjs

0.65

XmlEnum

0.64

Activations Density 0.152%

references to programming concepts and structures

Tokens after variable names or symbols

repeated integer types

No Comments

No Known Activations