INDEX

Explanations

the word "rule" followed by other words used in legal contexts

oai_token-act-pair · gemini-2.0-flash

rule

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

expandindo

-0.73

 ***!

-0.71

TagMode

-0.70

abestanden

-0.69

AndEndTag

-0.66

Legături

-0.63

 &___

-0.62



-0.61

tvguidetime

-0.61

 متعلقه

-0.60

POSITIVE LOGITS

bleau

0.51

lecteurs

0.48

 MessageBoxIcon

0.45

 onCancelled

0.44

bres

0.41

fares

0.40

endente

0.40

ệnh

0.40

fare

0.40

ABAJO

0.40

Activations Density 4.611%

the word "rule" followed by other words used in legal contexts

rule

No Comments

No Known Activations