INDEX

Explanations

words such as "this", "that", "what", "you" that begin phrases, along with ordinal numbers and words associated with memory.

oai_token-act-pair · 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

AndEndTag

-0.65

ódó

-0.65

-0.63

autoIncrement

-0.62

ContentAsync

-0.60

SPATH

-0.59

middels

-0.57

::~

-0.57

NOPQRST

-0.56

AccessorTable

-0.56

POSITIVE LOGITS

 choice

0.47

 plot

0.44

 tiết

0.44

 chegada

0.44

wnia

0.43

 person

0.43

makeConstraints

0.42

ANS

0.42

گز

0.42

出版年

0.42

Activations Density 0.935%

words such as "this", "that", "what", "you" that begin phrases, along with ordinal numbers and words associated with memory.

No Comments

No Known Activations