INDEX

Explanations

names of locations, particularly towns and geographic features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DeleteBehavior

-0.81

 mergeFrom

-0.72

 >=",

-0.71

 GetEnumerator

-0.69

 AssemblyProduct

-0.69

 BoxFit

-0.68

HtmlAttribute

-0.68

CloseOperation

-0.67

rawDesc

-0.67

 AssemblyCulture

-0.62

POSITIVE LOGITS

 resident

0.73

 residents

0.71

 area

0.61

 native

0.61

 Area

0.61

 Chamber

0.59

 community

0.58

 Public

0.58

area

0.56

based

0.56

Activations Density 0.214%

names of locations, particularly towns and geographic features

No Comments

No Known Activations