INDEX

Explanations

references to influences and relationships in a personal or professional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

ArgsConstructor

-0.94

ConstraintMaker

-0.71

 فريبيس

-0.66

 NSCoder

-0.65

 intStringLen

-0.65

脚注の使い方

-0.64

ंदीखरीदारी

-0.61

 يتيمه

-0.60

Portale

-0.59

 ModelExpression

-0.59

POSITIVE LOGITS

 mentoring

0.71

 nurturing

0.62

 hiring

0.61

 Mentoring

0.60

 mentorship

0.59

 training

0.56

 nurture

0.54

 nurtured

0.53

庇

0.52

 hire

0.51

Activations Density 0.261%

references to influences and relationships in a personal or professional context

No Comments

No Known Activations