INDEX

Explanations

terms and phrases related to research methodologies and settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

şek

-0.52

Specific

-0.49

 działania

-0.44

 positifs

-0.43

 spécifiques

-0.43

quate

-0.42

спонд

-0.41

 noqa

-0.41

 struk

-0.41

 estan

-0.40

POSITIVE LOGITS

 rare

0.77

rare

0.76

 rarely

0.71

 unsur

0.70

 unusual

0.70

 sadly

0.69

complexContent

0.67

WriteAttribute

0.66

 ujednoznacz

0.66

 rarity

0.66

Activations Density 0.388%

terms and phrases related to research methodologies and settings

No Comments

No Known Activations