INDEX

Explanations

the word "has" followed by a verb

oai_token-act-pair · gemini-2.0-flash

has

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 betweenstory

-0.60

väll

-0.58

MigrationBuilder

-0.57

AccessorTable

-0.56

行政区划

-0.55

AndEndTag

-0.54

igshid

-0.52

kuu

-0.52

 DbSet

-0.51

/**

-0.51

POSITIVE LOGITS

 kasarigan

0.45

aksikan

0.45

 numerus

0.45

cetes

0.45

ähren

0.44

 vesti

0.44

انظر

0.43

곱

0.43

abetes

0.43

 Fichier

0.43

Activations Density 1.442%

the word "has" followed by a verb

has

No Comments

No Known Activations