INDEX

Explanations

numerical data and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

enumi

-0.85

 AssemblyVersion

-0.76

}}}

-0.74

GOTREF

-0.72

\}\\

-0.72

waitKey

-0.71

 Cath

-0.70

 Allociné

-0.70

 بيها

-0.70

ESTRE

-0.69

POSITIVE LOGITS

0.96

IBinder

0.67

我一

0.62

pylene

0.59

testens

0.59

১

0.58

ZoneId

0.58

ONE

0.57

١

0.57

 geholfen

0.56

Activations Density 0.586%

numerical data and specifications

No Comments

No Known Activations