INDEX

Explanations

various forms of quotations and their meanings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.74

 oprot

-0.70

 jLabel

-0.67

 GenerationType

-0.59

 مرئيه

-0.58

 Oedipus

-0.58

 الرياضيه

-0.58

 يتيمه

-0.57

 rhetor

-0.57

saraba

-0.56

POSITIVE LOGITS

Personendaten

0.62

邦

0.57

:✨

0.56

AutoField

0.56

self

0.50

translated

0.50

ScopeManager

0.49

 traduire

0.48

translates

0.47

awaiter

0.47

Activations Density 0.124%

various forms of quotations and their meanings

No Comments

No Known Activations