INDEX

Explanations

uses of the word "short", and instances of numbers followed by "yards" or "weeks"

oai_token-act-pair · gemini-2.0-flash

short

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

 måneder

-0.51

JNIEnv

-0.44

Wire

-0.44

ůměr

-0.44

 évek

-0.43

NullException

-0.43

 décontract

-0.43

LEncoder

-0.43

 verseny

-0.42

IntoConstraints

-0.42

POSITIVE LOGITS

 short

2.27

 Short

1.91

short

1.89

Short

1.87

 SHORT

1.79

SHORT

1.63

 fhort

1.39

短

1.34

 shor

1.30

 corto

1.23

Activations Density 1.922%

uses of the word "short", and instances of numbers followed by "yards" or "weeks"

short

No Comments

No Known Activations