INDEX

Explanations

phrases that indicate allowance or facilitation of actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 مشين

-0.56

ReusableCell

-0.54

 conflictos

-0.51

siella

-0.50

brunn

-0.50

WebServlet

-0.49

 realidade

-0.49

ilene

-0.49

 seguintes

-0.47

 ramas

-0.47

POSITIVE LOGITS

parsedMessage

0.76

IndentedString

0.73

 للاسماء

0.72

uxxxx

0.68

 Réponses

0.68

 مرئيه

0.67

AppCompat

0.67

 saites

0.67

 виправивши

0.67

تقاوى

0.66

Activations Density 0.163%

phrases that indicate allowance or facilitation of actions

No Comments

No Known Activations