INDEX

Explanations

assignments of error in legal documents or procedures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"Aim", "Error", or "Mechanism" headers

np_acts-logits-general · gemini-2.0-flash

numbered aims or errors

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lastIndexOf

-0.42

 naturellement

-0.41

yarnpkg

-0.41

 Estre

-0.40

-0.38

 للمعارف

-0.36

 SPDX

-0.36

 cortes

-0.35

reise

-0.35

ванович

-0.35

POSITIVE LOGITS

第

0.99

\#

0.96

 Nummer

0.95

№

0.92

$\#

0.91

 thứ

0.88

 numbered

0.85

第

0.85

#"

0.83

Activations Density 0.998%

assignments of error in legal documents or procedures

"Aim", "Error", or "Mechanism" headers

numbered aims or errors

No Comments

No Known Activations