INDEX

Explanations

references to the number one

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

one

-1.14

one

-0.71

 satu

-0.64

One

-0.59

 одного

-0.59

uno

-0.58

 één

-0.57

de

-0.56

One

-0.56

by

-0.54

POSITIVE LOGITS

tagHelperRunner

1.11

+#+#

0.99

 Theſe

0.88

Personendaten

0.80

ScopeManager

0.78

KommentareTeilen

0.77

تقاوى

0.76

\{\\

0.75

Tikang

0.75

новништво

0.74

Activations Density 0.069%

references to the number one

No Comments

No Known Activations