INDEX

Explanations

references to medical classifications and grading systems

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

Grading or classifying something

np_acts-logits-general · gemini-2.0-flash

grades and classification levels

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 سكانية

-0.61

usammen

-0.56

 EconPapers

-0.49

IUrlHelper

-0.46

ובת

-0.46

lış

-0.46

󠁴

-0.46

pédie

-0.45

tillery

-0.45

 haystack

-0.45

POSITIVE LOGITS

 rating

1.80

 grade

1.75

 rated

1.63

 Grade

1.58

 ratings

1.52

 Rating

1.50

 grades

1.50

Grade

1.47

 classification

1.45

grade

1.43

Activations Density 0.792%

references to medical classifications and grading systems

Grading or classifying something

grades and classification levels

No Comments

No Known Activations