INDEX

Explanations

terms related to personal development and spiritual growth

oai_token-act-pair · gpt-4o-mini Triggered by @bot

before "is", "may", "will", or "can"

np_acts-logits-general · gemini-2.0-flash

person roles followed by pronouns

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 were

-0.61

 yourselves

-0.56

 weren

-0.52

were

-0.51

 själva

-0.50

weren

-0.50

ArrowToggle

-0.50

PASSED

-0.50

ługo

-0.50

nameof

-0.49

POSITIVE LOGITS

 himself

1.07

himself

0.93

who

0.87

 whom

0.80

 magát

0.79

 quien

0.79

 kendisi

0.76

MLLoader

0.75

 seinem

0.74

 herself

0.73

Activations Density 0.523%

terms related to personal development and spiritual growth

before "is", "may", "will", or "can"

person roles followed by pronouns

No Comments

No Known Activations