INDEX

Explanations

programming-related terms and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 tinta

-0.44

 short

-0.42

ाहरण

-0.40

を狙

-0.39

 certo

-0.38

orne

-0.38

-0.37

を目指

-0.37

திய

-0.36

fora

-0.36

POSITIVE LOGITS

BeginInit

0.91

 فريبيس

0.89

IVEREF

0.88

MigrationBuilder

0.86

expandindo

0.86

 صوتيه

0.85

0.78

UserScript

0.74

ArrowToggle

0.72

 itſelf

0.72

Activations Density 0.135%

programming-related terms and syntax

No Comments

No Known Activations