INDEX

Explanations

references to figures and diagrams in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 defaultstate

-0.54

aç

-0.47

âu

-0.46

ⓧ

-0.45

קרי

-0.44

ThroughAttribute

-0.44

/**/*.

-0.44

hagen

-0.43

 judged

-0.43

 nation

-0.43

POSITIVE LOGITS

 diagram

0.95

setVerticalGroup

0.94

 Schematic

0.94

 schematic

0.91

Schematic

0.87

 Diagram

0.81

 diagrams

0.81

 illustration

0.80

 المعيارى

0.79

 Illustration

0.78

Activations Density 0.748%

references to figures and diagrams in the text

No Comments

No Known Activations