INDEX

Explanations

snippets of an internet chat containing URLs and Linux-related terms like "ubuntu" and "debian"

oai_token-act-pair · gemini-2.0-flash

diverse non-English and code-related terms

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

Ubuntu Linux

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

engertian

-0.59

plication

-0.57

GetAsync

-0.56

haviors

-0.56

petto

-0.55

ImageContext

-0.54

PostExecute

-0.54

ρκ

-0.54

 دیکھیے

-0.53

vernote

-0.53

POSITIVE LOGITS

 الحره

0.60

fromnode

0.49

 JpaRepository

0.47

évaluateur

0.46

Dış

0.45

허

0.45

 ogóle

0.45

[]:

0.44

Muffin

0.42

}")]

0.41

Activations Density 1.430%

snippets of an internet chat containing URLs and Linux-related terms like "ubuntu" and "debian"

diverse non-English and code-related terms

Ubuntu Linux

No Comments

No Known Activations