INDEX

Explanations

instances of the word "os."

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

 nakalista

-0.66

◀

-0.60

 autorytatywna

-0.59

 distanciation

-0.58

 Dage

-0.58

 bezeichneter

-0.58

 препратки

-0.57

pkey

-0.56



-0.56

 agré

-0.56

POSITIVE LOGITS

os

4.20

OS

3.03

os

2.54

Os

2.35

Os

2.23

OS

2.10

osk

1.54

osz

1.48

osy

1.34

osc

1.29

Activations Density 0.065%

instances of the word "os."

No Comments

No Known Activations