INDEX

Explanations

elements related to human experiences and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 للمعارف

-0.70

basicConfig

-0.61

 المعيارى

-0.60

APORE

-0.58

 surla

-0.57

 ويكيميديا

-0.56

ględ

-0.55

 كومونز

-0.54

Autoritní

-0.53

modelBuilder

-0.53

POSITIVE LOGITS

queryInterface

0.71

 process

0.58

 ceremony

0.57

 Dign

0.56

 processo

0.56

 proceso

0.55

assisted

0.54

 proses

0.53

hearsed

0.52

Assisted

0.51

Activations Density 0.619%

elements related to human experiences and interactions

No Comments

No Known Activations