INDEX

Explanations

possessive pronouns and words relating to writing or recounting events

oai_token-act-pair · gemini-2.0-flash

Experiences

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UserScript

-0.72

DoubleQuotes

-0.65

onViewCreated

-0.60

OGND

-0.59

tvguidetime

-0.58

ViewImports

-0.58

 NSCoder

-0.56

 unknownFields

-0.54

makeConstraints

-0.53

RuleContext

-0.52

POSITIVE LOGITS

 experiences

0.77

 relationship

0.70

 journey

0.69

 interaction

0.65

 interactions

0.64

 experience

0.61

 experiencias

0.59

relationship

0.59

 career

0.58

journey

0.58

Activations Density 0.697%

possessive pronouns and words relating to writing or recounting events

Experiences

No Comments

No Known Activations