INDEX

Explanations

references to various associations and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ChildScrollView

-0.69

 tecn

-0.66

<!--[

-0.65

 Marcell

-0.64

Jakub

-0.63

 ventr

-0.63

Nog

-0.62

 Ehrlich

-0.62

 preci

-0.62

utilité

-0.62

POSITIVE LOGITS

 Association

2.39

 association

2.26

 associations

2.20

 ASSOCIATION

2.17

 Associations

2.17

Association

2.16

association

2.04

associations

1.90

Associations

1.89

 Assn

1.77

Activations Density 0.065%

references to various associations and their relationships

No Comments

No Known Activations