INDEX

Explanations

references to research methodologies and study designs

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

staticmethod

-0.64

Tikang

-0.61

Unmarshaller

-0.59

SIMPLE

-0.58

 linkovi

-0.57

 univariate

-0.56

 simplicity

-0.55

 Италијани

-0.55

 plebe

-0.54

 mało

-0.53

POSITIVE LOGITS

 larger

1.48

 full

1.41

 bigger

1.40

 Larger

1.23

本格

1.22

full

1.22

larger

1.22

Larger

1.21

 formal

1.18

bigger

1.16

Activations Density 0.975%

references to research methodologies and study designs

No Comments

No Known Activations