INDEX

Explanations

phrases related to instructions or directives

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

First person pronouns

np_acts-logits-general · gemini-2.0-flash

speaker or recipient pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 myself

-0.89

 yourself

-0.84

GEBURTSDATUM

-0.83

myself

-0.80

yourself

-0.77

 oneself

-0.76

 myſelf

-0.70

 Yourself

-0.69

 ourselves

-0.68

 transfieras

-0.67

POSITIVE LOGITS

us

0.97

me

0.74

my

0.66

RegressionTest

0.58

 нас

0.57

our

0.56

 plaintiff

0.54

 plaintiffs

0.54

 bizi

0.53

 conmigo

0.53

Activations Density 0.441%

phrases related to instructions or directives

First person pronouns

speaker or recipient pronouns

No Comments

No Known Activations