INDEX

Explanations

names of individuals and associated medical credentials

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

references to medical professionals and institutions

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

names and titles

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

thral

-0.54

bootstrapcdn

-0.53

MLLoader

-0.50

 postIndex

-0.50

DebuggerStep

-0.49

プリング

-0.46

 antic

-0.45

 Bunch

-0.45

 rivel

-0.45

estors

-0.44

POSITIVE LOGITS

UserScript

0.84

webElementXpaths

0.67

 препратки

0.67

 WaitForSeconds

0.65

RTSC

0.65

 Мексичка

0.63

RTEE

0.63

例句

0.61

 <<<<<<<<<<<<<<

0.60

\{\\

0.60

Activations Density 0.073%

names of individuals and associated medical credentials

references to medical professionals and institutions

names and titles

No Comments

No Known Activations