INDEX

Explanations

proper nouns, particularly names and titles associated with notable individuals or organizations

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

-0.62

tagHelperRunner

-0.58

HtmlAttribute

-0.55

BeginContext

-0.54

hdashline

-0.49

 Pilate

-0.49

AnimationsModule

-0.49

jeo

-0.48

onets

-0.47

 Valhalla

-0.47

POSITIVE LOGITS

Portale

0.70

 Biôgrafia

0.67

цезда

0.67

 oprot

0.66

 doInBackground

0.65

fjspx

0.61

 AssemblyVersion

0.59

GeneratedMessage

0.59

TagMode

0.57

routeProvider

0.55

Activations Density 1.006%

proper nouns, particularly names and titles associated with notable individuals or organizations

No Comments

No Known Activations