INDEX

Explanations

words related to medical procedures and studies

oai_token-act-pair · gemini-2.0-flash

foreign or transliterated words and phrases

np_token-act-pair-logits · gpt-4o-mini

surgical procedures

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.91

 InputDecoration

-0.71

featureID

-0.70

UserScript

-0.69

Geplaatst

-0.68

enderror

-0.65

TagMode

-0.64

<",

-0.64

بوابة

-0.64

writeField

-0.64

POSITIVE LOGITS

rů

0.48

cy

0.45

 Thomas

0.43

zewski

0.43

ουργ

0.43

 masas

0.42

 used

0.42

 einsch

0.42

 ever

0.41

 масса

0.41

Activations Density 1.161%

words related to medical procedures and studies

foreign or transliterated words and phrases

surgical procedures

No Comments

No Known Activations