INDEX

Explanations

symbols and mathematical elements used in scientific or technical contexts

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

saraba

-0.78

 >=",

-0.77

AxisAlignment

-0.64

发表于

-0.64

脚注の使い方

-0.64

скажите

-0.62

setupUi

-0.62

.');

-0.61

anskje

-0.60

 BoxDecoration

-0.59

POSITIVE LOGITS

NA

0.88

 none

0.87

NA

0.85

 unknown

0.83

TBD

0.80

TBA

0.77

none

0.77

 undetermined

0.75

Unknown

0.75

unknown

0.74

Activations Density 0.890%

symbols and mathematical elements used in scientific or technical contexts

No Comments

No Known Activations