INDEX

Explanations

references to new developments or changes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 hinweg

-0.51

PMID

-0.48

 scanf

-0.47

 PMID

-0.46

related

-0.45

propTypes

-0.44

 fandoms

-0.44

reuters

-0.44

fortawesome

-0.43

 usług

-0.42

POSITIVE LOGITS

new

1.31

 newly

1.10

 nieuwe

1.08

new

1.06

 новом

1.05

 nuevo

1.05

 newest

1.03

 nowej

1.02

 новой

1.02

 nueva

1.02

Activations Density 0.108%

references to new developments or changes in various contexts

No Comments

No Known Activations