INDEX

Explanations

references to experimental methods and results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

MigrationBuilder

-0.57

Rohy

-0.56

randrange

-0.55

 genetics

-0.52

 genética

-0.51

 USERS

-0.50

Népesség

-0.49

RemoteException

-0.48

LLocation

-0.48

OGND

-0.48

POSITIVE LOGITS

 prepared

0.77

 samples

0.76

 composites

0.68

 synthesized

0.67

 Prepared

0.67

prepared

0.65

 Samples

0.64

出版年

0.62

 fabricated

0.61

 sample

0.61

Activations Density 1.731%

references to experimental methods and results

No Comments

No Known Activations