INDEX

Explanations

the word "desire" and, to a lesser extent, words related to size and style

oai_token-act-pair · gemini-2.0-flash

desire

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Odkazy

-0.69

verwijspagina

-0.68

 Мексичка

-0.68

 transférez

-0.65

addContainerGap

-0.64

principalColumn

-0.64

 estekak

-0.63

 kasarigan

-0.63

prnewswire

-0.63

 tartalomajánló

-0.61

POSITIVE LOGITS

 réguli

0.45

sub

0.45

makeText

0.45

 présentés

0.45

 hunger

0.45

ерт

0.44

 hambre

0.44

 terminée

0.44

ffine

0.43

elt

0.42

Activations Density 0.947%

the word "desire" and, to a lesser extent, words related to size and style

desire

No Comments

No Known Activations