INDEX

Explanations

references to self-referential terms and concepts pertaining to identity

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

openConnection

-0.66

ември

-0.63

Wha

-0.59

podar

-0.58

YTICAL

-0.57

 Racine

-0.57

CreateMap

-0.57

Hos

-0.57

estacks

-0.56

astify

-0.56

POSITIVE LOGITS

 Roskov

0.85

 Itself

0.85

 itself

0.83

 betweenstory

0.81

itself

0.79

 sendiri

0.68

 protoimpl

0.67

LookAnd

0.65

 تضيفلها

0.65

本身

0.65

Activations Density 0.061%

references to self-referential terms and concepts pertaining to identity

No Comments

No Known Activations