INDEX

Explanations

the words "left" and "right" and "horizontal"

oai_token-act-pair · gemini-2.0-flash

side indicators in user interfaces

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

left or right

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

ConstraintMaker

-0.63

 likes

-0.52

 left

-0.48

 ujednoznacz

-0.46

 oublier

-0.45

ultades

-0.45

 passés

-0.43

niak

-0.43

SBATCH

-0.43

Left

-0.42

POSITIVE LOGITS

enderror

0.65

ništvo

0.61

 насељу

0.61

帖最后由

0.55

 SafeMath

0.55

上角

0.55

 Chwiliwch

0.55

writeField

0.54

 kasarigan

0.53

buttonBar

0.53

Activations Density 1.091%

the words "left" and "right" and "horizontal"

side indicators in user interfaces

left or right

No Comments

No Known Activations