INDEX

Explanations

author initials with some false positives

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

<bos>

-0.70

 мѣ

-0.48

تقاوى

-0.48

 jspb

-0.42

 AssemblyTitle

-0.41

ின்

-0.40

hyrchwyd

-0.40

ついて

-0.40

ніципа

-0.40

 bels

-0.40

POSITIVE LOGITS

fromnode

0.74

AndEndTag

0.70

المراجع

0.59

HtmlAttribute

0.59

رشف

0.57

nologue

0.56

]")]

0.55

rostis

0.54

ArgumentParser

0.54

 références

0.54

Activations Density 1.091%

author initials with some false positives

No Comments

No Known Activations