INDEX

Explanations

code elements and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ConverterFactory

-0.57

'][$

-0.52

 виправивши

-0.51

ChildScrollView

-0.48

endsection

-0.46

 '\\;'

-0.46

endforeach

-0.46

*)&

-0.45

 GoogleFonts

-0.45

``,

-0.45

POSITIVE LOGITS

 فريبيس

0.89

Jîn

0.67

ConstraintMaker

0.63

 argint

0.61

 autorytatywna

0.60

تفصیلات

0.59

 fieldNum

0.58

Билгалдахарш

0.58

 eccell

0.58

 privilégi

0.57

Activations Density 0.412%

code elements and structures

No Comments

No Known Activations