INDEX

Explanations

phrases emphasizing self-awareness and self-referential themes

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

"self" or its variations

np_acts-logits-general · gemini-2.0-flash

words starting with self-

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enschaften

-0.62

 geweest

-0.56

ViewFeatures

-0.54

IntoConstraints

-0.50

amazonaws

-0.50

setViewName

-0.50

 coû

-0.49

 cuer

-0.49

 fidélité

-0.48

Glej

-0.48

POSITIVE LOGITS

 self

1.01

 Self

0.89

 SELF

0.83

Self

0.82

ValueStyle

0.82

SELF

0.70

Etr

0.68

Selbst

0.66

 Selbst

0.65

 introspection

0.64

Activations Density 0.040%

phrases emphasizing self-awareness and self-referential themes

"self" or its variations

words starting with self-

No Comments

No Known Activations