INDEX

Explanations

references to online platforms or portals

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

libft

-0.67

bloomberg

-0.57

 ters

-0.56

новништво

-0.56

 buss

-0.56

Buss

-0.54

 Ters

-0.53

ofil

-0.52

 stati

-0.51

ild

-0.51

POSITIVE LOGITS

 portal

1.42

 Portal

1.29

 portals

1.12

portal

1.12

Portal

1.04

 gateway

0.87

 knee

0.81

DeleteBehavior

0.77

 portail

0.77

knee

0.76

Activations Density 0.064%

references to online platforms or portals

No Comments

No Known Activations