INDEX

Explanations

the word "man," or words including "man" as a prefix or suffix

oai_token-act-pair · gemini-2.0-flash

man

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nakalista

-0.74

CloseOperation

-0.71

subpackage

-0.70

 onCreateView

-0.66

InputTagHelper

-0.60

XmlRootElement

-0.59

ustimmung

-0.58

Dichloropropane

-0.57

stdc

-0.56

PhysRevLett

-0.56

POSITIVE LOGITS

 Roskov

0.49

 auft

0.45

 otomatig

0.44

 esternos

0.43

sions

0.42

īgs

0.42

 كومونز

0.41

onies

0.41

 bizi

0.39

Sys

0.39

Activations Density 0.252%

the word "man," or words including "man" as a prefix or suffix

man

No Comments

No Known Activations