INDEX

Explanations

phrases related to image processing errors or notifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

kor

-0.58

APO

-0.40

ter

-0.40

sok

-0.38

 erken

-0.36

nik

-0.35

ob

-0.35

 че

-0.34

om

-0.34

距

-0.33

POSITIVE LOGITS

rungsseite

0.98

Personensuche

0.91

webElementXpaths

0.89

 ſtate

0.87

 uſe

0.86

 itſelf

0.85

 raiſ

0.82

 neceff

0.82

 themſelves

0.82

 noDo

0.82

Activations Density 0.038%

phrases related to image processing errors or notifications

No Comments

No Known Activations