INDEX

Explanations

sections of text introducing or describing entities and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

andExpect

-0.52

Personensuche

-0.52

Revenir

-0.51

lineno

-0.49

GenerationType

-0.49

 calldata

-0.49

 MainAxisSize

-0.49

WebElementEntity

-0.48

QMetaType

-0.48

expandindo

-0.48

POSITIVE LOGITS

About

0.94

ABOUT

0.93

 About

0.88

InputBorder

0.87

 background

0.79

Acerca

0.77

about

0.76

 Background

0.75

 ABOUT

0.75

 company

0.74

Activations Density 0.113%

sections of text introducing or describing entities and their characteristics

No Comments

No Known Activations