INDEX

Explanations

programming-related terminology and commands for managing data or resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InputBorder

-1.13

 <=",

-1.07

IntoConstraints

-0.97

+:+

-0.95

 nahilalakip

-0.95

bootstrapcdn

-0.94

 disambiguazione

-0.94

ftagPool

-0.93

RectangleBorder

-0.92

WebVitals

-0.91

POSITIVE LOGITS

0.43

かない

0.40

0.39

↵↵

0.38

0.37

0.36

↵

0.36

えません

0.36

extrême

0.35

Activations Density 0.592%

programming-related terminology and commands for managing data or resources

No Comments

No Known Activations