INDEX

Explanations

comparisons of effectiveness and quality among products or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Einfach

-0.57

اریخ

-0.49

 Kopf

-0.47

역

-0.46

первых

-0.45

เภ

-0.44

umerable

-0.44

itária

-0.43

ষ

-0.43

pierw

-0.43

POSITIVE LOGITS

 '\\;'

0.67

 invokingState

0.67

NewUrlParser

0.64

 jopa

0.62

Bahkan

0.62

WebControls

0.59

queryInterface

0.58

 getItemCount

0.56

 zelfs

0.56

Kedua

0.55

Activations Density 0.230%

comparisons of effectiveness and quality among products or entities

No Comments

No Known Activations