INDEX

Explanations

references to family names and affiliations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ketiga

-0.51

 Sahne

-0.50

enumi

-0.49

enumii

-0.49

 }}$.

-0.49

 adentro

-0.45

fø

-0.43

__["

-0.43

andina

-0.43

ulto

-0.43

POSITIVE LOGITS

 CURIAM

0.81

 JpaRepository

0.81

 cherchés

0.71

 family

0.67

sizeCache

0.67

abestanden

0.67

 betweenstory

0.66

unknownFields

0.65

MigrationBuilder

0.64

 INTERESAR

0.63

Activations Density 0.130%

references to family names and affiliations

No Comments

No Known Activations