INDEX

Explanations

references to properties or characteristics in a technical or scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

awtextra

-0.69

XmlAccessType

-0.66

AndEndTag

-0.65

WriteTagHelper

-0.63

ijnt

-0.60

ージョン

-0.59

 estimés

-0.58

xler

-0.58

 Schmitz

-0.57

*********/

-0.56

POSITIVE LOGITS

 prop

1.48

 Prop

1.26

Prop

1.16

prop

1.12

 props

1.08

 PROP

1.05

 Props

0.90

PROP

0.83

 hydro

0.77

 propeller

0.75

Activations Density 0.073%

references to properties or characteristics in a technical or scientific context

No Comments

No Known Activations