INDEX

Explanations

references to attracting attention or interest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

/**

-0.85

<h6>

-0.79

ptonshire

-0.75

<em>

-0.74

-0.72

PathParam

-0.70

<h3>

-0.70

 jPanel

-0.70

jod

-0.69

<h5>

-0.68

POSITIVE LOGITS

 Attra

1.54

Attra

1.53

 attracted

1.53

 attract

1.52

 attraction

1.52

 attracting

1.51

 Attraction

1.46

attra

1.46

 attra

1.45

 attractions

1.44

Activations Density 0.094%

references to attracting attention or interest

No Comments

No Known Activations