INDEX

Explanations

phrases that indicate hypocrisy or inconsistency in people's actions or statements

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

Possessive pronouns

np_acts-logits-general · gemini-2.0-flash

possessive pronouns and determiners

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

herself

-0.70

contentLoaded

-0.59

himself

-0.58

queryInterface

-0.56

}\]

-0.55

เอง

-0.55

lui

-0.52

selves

-0.50

 Himself

-0.50

DockStyle

-0.49

POSITIVE LOGITS

 their

1.90

 your

1.90

 seus

1.79

his

1.77

seu

1.70

 suas

1.64

 своих

1.62

 своего

1.57

sua

1.54

 své

1.53

Activations Density 2.181%

phrases that indicate hypocrisy or inconsistency in people's actions or statements

Possessive pronouns

possessive pronouns and determiners

No Comments

No Known Activations