INDEX

Explanations

concepts or qualities related to uniqueness and compatibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 storici

-0.53

 storico

-0.49

CKS

-0.49

 GenerationType

-0.48

 باخ

-0.48

igheid

-0.48

 witnesses

-0.48

Zuw

-0.47

FORMA

-0.47

 conmigo

-0.46

POSITIVE LOGITS

verwijspagina

0.85

évaluateur

0.71

fjspx

0.71

Tikang

0.68

تقاوى

0.61

 protoimpl

0.60

ArgumentParser

0.59

Хьажоргаш

0.58

tableFuture

0.56

DrawerToggle

0.56

Activations Density 0.353%

concepts or qualities related to uniqueness and compatibility

No Comments

No Known Activations