INDEX

Explanations

technical comments or code structures related to file handling and error management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

SequentialGroup

-0.99

TagMode

-0.94

 autorytatywna

-0.90

PreferredItem

-0.80

 noqa

-0.79

saraba

-0.79

CloseOperation

-0.78

 GenerationType

-0.77

 saites

-0.75

 RouterModule

-0.72

POSITIVE LOGITS

<eos>

0.65

kmäler

0.55

 assunto

0.55

 tendenza

0.53

 învă

0.50

enderror

0.50

 dolgo

0.47

 berani

0.46

الإنجليزية

0.46

↵

0.45

Activations Density 0.037%

technical comments or code structures related to file handling and error management

No Comments

No Known Activations