INDEX

Explanations

mentions of secrecy or things not being available to the public

oai_token-act-pair · gemini-2.0-flash

phrases indicating secrecy or hidden contexts

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

behind

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

antMatchers

-0.56

SourceChecksum

-0.53

tvguidetime

-0.53

Sprintf

-0.53

awaiter

-0.51

دانشنامهٔ

-0.49

 JpaRepository

-0.49

发表于

-0.48

MigrationBuilder

-0.48

POSITIVE LOGITS

 fût

0.59

nemen

0.58

utique

0.57

BeginInit

0.57

őle

0.56

RenderAtEndOf

0.56

뀔

0.56

 døde

0.55

 trouvait

0.54

Collegamenti

0.53

Activations Density 12.884%

mentions of secrecy or things not being available to the public

phrases indicating secrecy or hidden contexts

behind

No Comments

No Known Activations