INDEX

Explanations

formatting commands in a coding or typesetting context related to document settings

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

math and code formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.61

adaptiveStyles

-0.58

 purpoſe

-0.55

ьаж

-0.54

ſelves

-0.54

 curs

-0.52

 referenties

-0.51

 houſe

-0.50

)++;

-0.50

spesies

-0.49

POSITIVE LOGITS

تقاوى

0.41

 tartalomajánló

0.37

 falda

0.37

setPref

0.36

 buoni

0.36

 läßt

0.36

 muß

0.35

 buono

0.35

 estekak

0.34

WriteBarrier

0.34

Activations Density 0.026%

formatting commands in a coding or typesetting context related to document settings

math and code formatting

No Comments

No Known Activations

formatting commands in a coding or typesetting context related to document settings

math and code formatting

No Comments

No Known Activations