INDEX

Explanations

symbols and formatting related to mathematical expressions or datasets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ỡng

-0.56

 يتيمه

-0.56

 }^{(

-0.53

typeparam

-0.50

﹀

-0.50

Ass

-0.49

odas

-0.48

 schre

-0.48

angliski

-0.48

Sabato

-0.48

POSITIVE LOGITS

ValueStyle

0.81

 disponibilités

0.67

 aéreo

0.65

seamnă

0.61

UnknownFieldSet

0.61

 gravure

0.59

ConstraintMaker

0.59

 noqa

0.58

 Roskov

0.57

 betrug

0.55

Activations Density 0.221%

symbols and formatting related to mathematical expressions or datasets

No Comments

No Known Activations