INDEX

Explanations

terms related to attraction and appealing characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

/**

-0.84

PathParam

-0.79

<h6>

-0.77

 jPanel

-0.70

jod

-0.70

 AssemblyCulture

-0.69

гласно

-0.68

<em>

-0.68

<h3>

-0.67

setParameter

-0.66

POSITIVE LOGITS

 Attra

1.50

Attra

1.49

 attra

1.46

 attractiveness

1.44

 attracting

1.43

 attract

1.43

 attracted

1.42

 attraction

1.42

attra

1.39

 Attraction

1.36

Activations Density 0.125%

terms related to attraction and appealing characteristics

No Comments

No Known Activations