INDEX

Explanations

elements related to technical or programming contexts

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

manteau

-0.58

Château

-0.53

gements

-0.52

 onLoad

-0.51

 Thessal

-0.51

 Allegretto

-0.49

autoconfigure

-0.49

ecto

-0.49

 photographe

-0.48

 Crowd

-0.47

POSITIVE LOGITS

Pi

0.56

Ti

0.56

li

0.55

si

0.55

Ti

0.55

xi

0.54

Pi

0.53

 titanium

0.53

ti

0.53

transQ

0.53

Activations Density 0.713%

elements related to technical or programming contexts

No Comments

No Known Activations