INDEX

Explanations

terms related to statistical analysis and methods

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

 PopupWindow

-0.49

instrumental

-0.47

+#+#

-0.46

 echa

-0.46

💼

-0.46

 damit

-0.45

Shadow

-0.45

 Shadow

-0.45

Firm

-0.45

ής

-0.45

POSITIVE LOGITS

 ANOVA

0.79

 paired

0.73

paired

0.72

ANOVA

0.72

Paired

0.67

 Krus

0.67

verwijspagina

0.63

 Comparisons

0.62

Personensuche

0.62

 Student

0.62

Activations Density 1.111%

terms related to statistical analysis and methods

No Comments

No Known Activations