INDEX

Explanations

positive feedback and recommendations related to service experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Vidite

-0.72

 GoogleFonts

-0.59

PasswordEncoder

-0.57

PMailer

-0.56

 AppColors

-0.54

 MonoBehaviour

-0.53

GraphicsUnit

-0.52

viewBox

-0.52

DIPSETTING

-0.50

aarrggbb

-0.50

POSITIVE LOGITS

jalá

0.61

Diweddarwch

0.59

 csal

0.59

 مشين

0.56

 thumbs

0.55

}{*}{}

0.54

 незавершена

0.53

 hearted

0.53

 contigo

0.53

󠁢

0.52

Activations Density 0.084%

positive feedback and recommendations related to service experiences

No Comments

No Known Activations