INDEX

Explanations

discussions centered around community-level processes and dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 chi̍t

-0.53

OMON

-0.50

 XCTest

-0.49

Havolalar

-0.48

℗

-0.47

RVA

-0.46

LIK

-0.46

kungen

-0.46

ⓧ

-0.45

 NSCoder

-0.45

POSITIVE LOGITS

 level

1.80

level

1.50

 Level

1.41

Level

1.40

 LEVEL

1.40

 levels

1.38

 nivel

1.32

 nível

1.32

 niveau

1.30

 livello

1.23

Activations Density 0.260%

discussions centered around community-level processes and dynamics

No Comments

No Known Activations