INDEX

Explanations

references to alterations or adjustments in systems, processes, or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

jsonwebtoken

-0.58

UnknownFields

-0.54

ølge

-0.43

رشف

-0.43

 ✭✭

-0.42

 adicionais

-0.40

WritableDatabase

-0.40

izin

-0.40

 espirituales

-0.39

 nationalism

-0.39

POSITIVE LOGITS

 change

1.26

 Change

1.23

 Changing

1.22

 changing

1.17

 changed

1.16

Changing

1.14

 CHANGE

1.14

change

1.11

changing

1.10

 Changed

1.10

Activations Density 0.625%

references to alterations or adjustments in systems, processes, or roles

No Comments

No Known Activations