INDEX

Explanations

references to specific timeframes or points in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

TextWatcher

-0.54

 bolig

-0.51

 foglal

-0.49

KommentareTeilen

-0.48

任

-0.48

 textStatus

-0.48

قة

-0.46

 čern

-0.46

 esperando

-0.46

 instala

-0.46

POSITIVE LOGITS

Byr

0.94

By

0.93

By

0.88

by

0.80

bys

0.76

standers

0.73

 getBy

0.71

BY

0.68

means

0.68

eby

0.67

Activations Density 0.119%

references to specific timeframes or points in discussions

No Comments

No Known Activations