INDEX

Explanations

terms related to healthcare and medication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

jsxFileName

-0.61

})->

-0.58

LayoutStyle

-0.58

 referenties

-0.56

QMetaType

-0.49

 beginnetje

-0.47

шње

-0.47

enegro

-0.46

styleType

-0.46

'].'

-0.46

POSITIVE LOGITS

ließlich

0.55

 XCTest

0.54

webElementXpaths

0.53

dze

0.52

 ferrous

0.52

OrWhiteSpace

0.51

LLocation

0.50

 doInBackground

0.50

يان

0.50

related

0.50

Activations Density 1.034%

terms related to healthcare and medication

No Comments

No Known Activations