INDEX

Explanations

programming-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

EndGlobalSection

-0.76

DockStyle

-0.71

MarshalTo

-0.69

 VizieR

-0.65

Aiheesta

-0.64

AutoScaleMode

-0.63

KURZBESCHREIBUNG

-0.63

外部リンク

-0.62

orsese

-0.62

 propOrder

-0.62

POSITIVE LOGITS

 وتسجيلات

0.62

KommentareTeilen

0.54

omla

0.48

 Cypri

0.45

OLED

0.44

בור

0.44

icza

0.43

$<

0.43

Sch

0.43

://

0.42

Activations Density 0.006%

programming-related terminology

No Comments

No Known Activations