INDEX

Explanations

references to specific software or programming frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

帖最后由

-0.59

ousa

-0.52

gonic

-0.51

internalType

-0.51

nsyn

-0.51

SaveChangesAsync

-0.48

}{*}{

-0.48

<?

-0.48

antic

-0.48

isNaN

-0.48

POSITIVE LOGITS

 purpoſe

1.02

Efq

0.95

 ſtate

0.87

 cauſe

0.85

 reaſon

0.81

 myſelf

0.76

 houſe

0.76

 ſmall

0.75

 ſon

0.75

 uſe

0.74

Activations Density 0.075%

references to specific software or programming frameworks

No Comments

No Known Activations