INDEX

Explanations

references to programming concepts and technologies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

ItemBackground

-0.73

 ſon

-0.62

 houſe

-0.60

Portály

-0.58

 Maximus

-0.58

 caufe

-0.58

 Shakspeare

-0.58

oflavin

-0.57

 cauſe

-0.57

 correctes

-0.57

POSITIVE LOGITS

tvguidetime

0.64

 GenerationType

0.63

epi

0.57

 useEffect

0.52

wet

0.51

ep

0.51

bat

0.50

Dar

0.49

 tortured

0.49

 Moisture

0.49

Activations Density 3.097%

references to programming concepts and technologies

No Comments

No Known Activations