INDEX

Explanations

references to "active" or "actively engaged" systems and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 betweenstory

-0.88

IOM

-0.77

PMailer

-0.77

 Roskov

-0.74

Wann

-0.74

 GATT

-0.73

 Trumb

-0.73

 skak

-0.73

=&

-0.73

CloseOperation

-0.72

POSITIVE LOGITS

 active

3.31

 Active

3.07

Active

2.99

active

2.91

 ACTIVE

2.83

ACTIVE

2.53

 aktive

2.18

 actives

2.14

 aktiven

2.13

getActive

2.10

Activations Density 0.053%

references to "active" or "actively engaged" systems and processes

No Comments

No Known Activations