INDEX

Explanations

terms related to medical assessments and biological functions

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

after abbreviations or short words

np_acts-logits-general · gemini-2.0-flash

sum expansion, states plus

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

}}}}

-0.62

ised

-0.59

reportWebVitals

-0.59

SharedDtor

-0.53

ized

-0.51

ContentAsync

-0.51

 '*')

-0.51

?,?,

-0.51

 ſaid

-0.50

-</

-0.50

POSITIVE LOGITS

 AssemblyCompany

0.79

 AssemblyTitle

0.69

étit

0.61

RTGC

0.61

AndEndTag

0.61

 Picchu

0.57

ItemBackground

0.55

期刊论文

0.55

webElement

0.54

URLException

0.53

Activations Density 5.439%

terms related to medical assessments and biological functions

after abbreviations or short words

sum expansion, states plus

No Comments

No Known Activations