INDEX

Explanations

terms related to job roles and responsibilities in a professional or medical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

 autorytatywna

-0.98

 intptr

-0.87

 odkazy

-0.84

findpost

-0.82

twimg

-0.79

featureID

-0.79



-0.78

脚注の使い方

-0.78

EndProject

-0.77

]--;

-0.76

POSITIVE LOGITS

 clerk

0.67

 office

0.65

 receptionist

0.65

 clerical

0.64

 Clerk

0.64

 staff

0.64

 ufficio

0.61

 Office

0.59

 assistant

0.56

 clerks

0.55

Activations Density 0.230%

terms related to job roles and responsibilities in a professional or medical context

No Comments

No Known Activations