INDEX

Explanations

references to geographical locations and regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

httphttps

-0.80

ⓧ

-0.58

 Donegal

-0.52

 Administrativna

-0.48

 Bergen

-0.47

Marseille

-0.47

Extinguishing

-0.46

InitVars

-0.46

 Gaza

-0.45

 Duisburg

-0.45

POSITIVE LOGITS

ChildScrollView

0.69

ophan

0.66

 Tallahassee

0.65

toThrow

0.65

 DeWitt

0.64

 Dorothea

0.62

 Kele

0.61

 Thü

0.59

Capital

0.59

urlopen

0.58

Activations Density 0.184%

references to geographical locations and regions

No Comments

No Known Activations