INDEX

Explanations

phrases indicating involvement or actions related to a particular subject

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

TabStop

-0.61

 רבים

-0.60

LayoutInflater

-0.59

AutoField

-0.58

our

-0.54

addCell

-0.53

zeitige

-0.53

重要的

-0.51

로운

-0.51

 ролях

-0.51

POSITIVE LOGITS

ContentAsync

0.70

tvguidetime

0.61

MENAFN

0.58

 mahdollis

0.56

تقاوى

0.55

 estimés

0.53

âce

0.53

 확인함

0.51

alnız

0.51

 Rohing

0.51

Activations Density 1.046%

phrases indicating involvement or actions related to a particular subject

No Comments

No Known Activations