INDEX

Explanations

references to "Cal" and its various forms, likely related to California or its institutions

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

WebElementEntity

-0.69

Vidite

-0.68

bitField

-0.60

}{*}{}

-0.59

AppCompat

-0.56

 AssemblyCompany

-0.55

HttpPut

-0.55

endregion

-0.54

hoku

-0.54

rewsbury

-0.53

POSITIVE LOGITS

CAL

0.89

Cal

0.75

Cal

0.70

CAL

0.69

Calle

0.65

cal

0.64

Kal

0.64

cal

0.63

Kal

0.63

kal

0.62

Activations Density 0.083%

references to "Cal" and its various forms, likely related to California or its institutions

No Comments

No Known Activations