INDEX

Explanations

references to arguments and analyses made by various authors or scholars

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

Comes before verbs of communication

np_acts-logits-general · gemini-2.0-flash

names followed by arguments or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ruptedException

-0.76

ReusableCell

-0.74

extAlignment

-0.72

interopRequire

-0.71

 ModelExpression

-0.66

PropertyChanging

-0.65

原始内容存档于

-0.65

Obrázky

-0.65

ManagedBean

-0.64

ArgsConstructor

-0.63

POSITIVE LOGITS

 pointed

0.79

 suggested

0.75

 rightly

0.73

 suggests

0.72

 noted

0.70

 quoted

0.68

 suggest

0.68

 describes

0.65

指出

0.63

 observed

0.63

Activations Density 0.577%

references to arguments and analyses made by various authors or scholars

Comes before verbs of communication

names followed by arguments or statements

No Comments

No Known Activations