INDEX

Explanations

items in a list denoted by a letter

oai_token-act-pair · gemini-2.0-flash

technical terms and file descriptors

np_token-act-pair-logits · gpt-4o-mini

Non-English words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

!*\

-0.52

-0.51

inerja

-0.51

UserScript

-0.50

SourceChecksum

-0.49

Isk

-0.48

WireFormatLite

-0.47

سبة

-0.47

OpenHelper

-0.47

ifers

-0.46

POSITIVE LOGITS

 חיצוניים

0.71

 שוליים

0.56

 arşivlendi

0.53

jboss

0.52

synthesize

0.51

ValueStyle

0.48

 مشين

0.48

@"/

0.46

Παραπομπές

0.46

 FetchType

0.45

Activations Density 1.105%

items in a list denoted by a letter

technical terms and file descriptors

Non-English words

No Comments

No Known Activations