INDEX

Explanations

technical references to web and software components in programming

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

Passes

-0.46

hen

-0.41

pre

-0.41

 title

-0.40

PostMapping

-0.40

passes

-0.40

 added

-0.40

Pre

-0.39

add

-0.37

ures

-0.37

POSITIVE LOGITS

Diwedd

0.80

 Мексичка

0.72

AsUp

0.71

لكتر

0.70

 lenker

0.68

ंदीखरीदारी

0.67

endimiento

0.66

日閲覧

0.65

########.

0.65

 חיצוניים

0.65

Activations Density 0.044%

technical references to web and software components in programming

No Comments

No Known Activations