INDEX

Explanations

references to airlines and related terms, especially airline names

oai_token-act-pair · gemini-2.0-flash

technical terms or headers

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

Airports and Airlines

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

+#+#

-0.65

 étions

-0.57

 Partagez

-0.57

ाहरण

-0.57

 automatiques

-0.56

➟

-0.55

mybatisplus

-0.55

انجليز

-0.53

 devons

-0.52

SourceChecksum

-0.51

POSITIVE LOGITS

KURZBESCHREIBUNG

0.59

 חיצוניים

0.56

expandindo

0.55

AndEndTag

0.51

 Administrativna

0.51

Chham

0.51

}]

0.46

 cycl

0.46

 AssemblyCulture

0.46

InvalidProtocol

0.46

Activations Density 0.393%

references to airlines and related terms, especially airline names

technical terms or headers

Airports and Airlines

No Comments

No Known Activations