INDEX

Explanations

references to religious texts, people, and concepts

oai_token-act-pair · gemini-2.0-flash

references to religious texts or figures

np_token-act-pair-logits · gpt-4o-mini

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cydow

-0.53

 AssemblyCompany

-0.45

壤

-0.42

Portail

-0.42

 AppComponent

-0.40

bentar

-0.40

 للمعارف

-0.39

Viel

-0.39

 lapangan

-0.38

 IUser

-0.38

POSITIVE LOGITS

Hebrews

0.77

 Mosaic

0.75

 Scripture

0.75

 Bible

0.74

 Exodus

0.74

 Jesus

0.74

 Hebrews

0.74

 Pharisees

0.73

 Apostle

0.72

 disciples

0.70

Activations Density 6.227%

references to religious texts, people, and concepts

references to religious texts or figures

the

No Comments

No Known Activations