INDEX

Explanations

technical terms and identifiers related to programming and multimedia formats

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

FFMPEG, ADPKD, Spring Harbor

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 hebat

-0.56

Tôi

-0.54

enumi

-0.52

 aislada

-0.52

 éstas

-0.50

 arşivlendi

-0.50

 ámbitos

-0.50

 ecológico

-0.50

 Kriege

-0.50

 Hauses

-0.49

POSITIVE LOGITS

processable

0.65

 UIAlert

0.64

NOPQRST

0.60

 Touchable

0.57

iffance

0.54

issory

0.53

wapV

0.53

iſten

0.53

CDCl

0.53

 Coca

0.52

Activations Density 7.963%

technical terms and identifiers related to programming and multimedia formats

FFMPEG, ADPKD, Spring Harbor

No Comments

No Known Activations