INDEX

Explanations

instances of the word "noticed"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 BorderRadius

-0.69

ItemBackground

-0.66

 EdgeInsets

-0.65

zzleHttp

-0.63

minus

-0.62

AxisAlignment

-0.59

ValueGenerated

-0.57

énario

-0.57

 MainAxisSize

-0.56

ništvo

-0.55

POSITIVE LOGITS

 noticed

2.24

 noticing

2.04

noticed

1.80

 spotted

1.76

 notice

1.62

 notices

1.57

 detected

1.54

 discovered

1.50

Spotted

1.50

 Spotted

1.48

Activations Density 0.127%

instances of the word "noticed"

No Comments

No Known Activations