INDEX

Explanations

words ending in 'o' in equations, programming terms and possibly names

oai_token-act-pair · gemini-2.0-flash

Code and math context

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Tembelea

-0.69

帖最后由

-0.65

AndEndTag

-0.61

Personendaten

-0.57

uxxxx

-0.55

CloseOperation

-0.54

 trajets

-0.53

----</

-0.53

ViewImports

-0.52

Aholisi

-0.52

POSITIVE LOGITS

 doInBackground

0.38

strado

0.38

 scuro

0.36

def

0.36

 initWith

0.35

 TextStyle

0.35

die

0.35

das

0.34

✳

0.34

da

0.34

Activations Density 1.503%

words ending in 'o' in equations, programming terms and possibly names

Code and math context

No Comments

No Known Activations