INDEX

Explanations

words and phrases related to scientific research and experiments, e.g., characterization, determination, and identification.

oai_token-act-pair · gemini-2.0-flash

characterize

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

featureID

-0.57

DockStyle

-0.56

enterOuterAlt

-0.55

HasForeignKey

-0.54

principalColumn

-0.52

OnInit

-0.50

NegativeButton

-0.50

wey

-0.49

IBOutlet

-0.47

приятие

-0.47

POSITIVE LOGITS

<bos>

0.69

 Normdatei

0.60

OOTDTY

0.59

znam

0.59

 XCTest

0.58

 DBNull

0.57

 discovered

0.55

aarrggbb

0.53

 onCancelled

0.53

]='\

0.51

Activations Density 2.692%

words and phrases related to scientific research and experiments, e.g., characterization, determination, and identification.

characterize

No Comments

No Known Activations