INDEX

Explanations

references to geographical locations and political entities

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

ChildScrollView

-0.54

mmation

-0.54

FunctionFlags

-0.53

hundred

-0.45

OLAR

-0.45

 União

-0.44

COLN

-0.44

XmlAccessType

-0.43

 trattano

-0.43

 kimi

-0.42

POSITIVE LOGITS

 province

1.30

 Province

1.18

省

0.98

 Provincial

0.97

province

0.96

 provincial

0.93

 governor

0.91

Province

0.90

 provincia

0.87

Provincial

0.86

Activations Density 0.128%

references to geographical locations and political entities

No Comments

No Known Activations