INDEX

Explanations

references to programming structures or constructs

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sasaran

-0.55

SharedDtor

-0.54

يميديا

-0.51

 dimaksud

-0.48

اهرة

-0.48

/-/

-0.47

PhysRevLett

-0.47

useNewUrlParser

-0.47

ţiei

-0.47

 zwar

-0.46

POSITIVE LOGITS

########.

0.89

 виправивши

0.86

RegressionTest

0.76

 Dernière

0.70

expandindo

0.66

">//

0.66

 continúas

0.65

 Otro

0.62

发表于

0.61

fjspx

0.61

Activations Density 0.373%

references to programming structures or constructs

No Comments

No Known Activations