INDEX

Explanations

start tokens that introduce new sections or topics within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

сылкі

-0.77

itects

-0.77

utdown

-0.76

脚注の使い方

-0.75

SDAY

-0.72

 toothpick

-0.71

olesome

-0.71

 notizia

-0.70

 Monfieur

-0.69

 pleaſure

-0.69

POSITIVE LOGITS

 series

1.84

 Series

1.81

Series

1.74

 SERIES

1.69

iseries

1.53

series

1.51

SERIES

1.50

 Serie

1.23

Serie

1.18

eries

1.16

Activations Density 0.046%

start tokens that introduce new sections or topics within a document

No Comments

No Known Activations