INDEX

Explanations

specific medical abbreviations and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

gug

-0.65

 собою

-0.64

됩

-0.64

newList

-0.63

jenner

-0.61

 restTemplate

-0.60

quiry

-0.60

GOTREF

-0.59

 Sturm

-0.58

JsonResponse

-0.58

POSITIVE LOGITS

Siddhartha

0.83

③

0.78

'{@

0.69

")[

0.66

>{@

0.66

 }^{(

0.66

'),

0.65

 Tant

0.65

 Hennessy

0.65

Carn

0.64

Activations Density 1.280%

specific medical abbreviations and terminology

No Comments

No Known Activations