INDEX

Explanations

nested parentheses and associated numerical data

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

+#+#

-0.68

########.

-0.58

digans

-0.55

Portale

-0.55

 bersi

-0.55

ologous

-0.54

ścic

-0.53

pirable

-0.52

modelBuilder

-0.52

!*\

-0.51

POSITIVE LOGITS

 printing

0.91

 Paper

0.87

 paper

0.85

 printer

0.83

Paper

0.82

 printers

0.80

 Printing

0.79

 Printer

0.77

印刷

0.77

Printing

0.77

Activations Density 0.233%

nested parentheses and associated numerical data

No Comments

No Known Activations