INDEX

Explanations

terms related to medical conditions and terminology

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

ending in specific suffixes

np_acts-logits-general · gemini-2.0-flash

anatomical, familial, categorical, phagia

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ukone

-0.44

 MongoClient

-0.43

elem

-0.40

TimeInterval

-0.39

 allt

-0.39

WireFormat

-0.38

 zestawie

-0.38

Pome

-0.38

djangoproject

-0.38

ugan

-0.38

POSITIVE LOGITS

eries

0.82

ía

0.75



0.74

Efq

0.70

ies

0.70

ries

0.69

 fince

0.69

 CreateTagHelper

0.68

ÍA

0.66

 Alloy

0.66

Activations Density 0.238%

terms related to medical conditions and terminology

ending in specific suffixes

anatomical, familial, categorical, phagia

No Comments

No Known Activations