INDEX

Explanations

occurrences of the word "up" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 doskon

-0.48

astéro

-0.47

 sessionFactory

-0.46

 która

-0.44

 /*#__

-0.43

retudo

-0.43

 dezelve

-0.43

.'.

-0.42

AddHtmlAttribute

-0.42

elstein

-0.42

POSITIVE LOGITS

up

1.18

Up

1.14

Up

1.07

up

0.98

UP

0.96

ups

0.95

Ups

0.84

UP

0.77

tup

0.75

UpDown

0.73

Activations Density 0.120%

occurrences of the word "up" in various contexts

No Comments

No Known Activations