INDEX

Explanations

references to specific academic affiliations and methods in research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

IsContent

-0.86

 Roskov

-0.85

AccessorTable

-0.65

 Normdatei

-0.65

 Wikispecies

-0.64

LookAnd

-0.64

Autoritní

-0.64

 ErrIntOverflow

-0.62

Portale

-0.61

 استنادى

-0.59

POSITIVE LOGITS

ت

1.08

parseInt

0.92

parseDouble

0.87

 parseInt

0.72

parseFloat

0.62

parseLong

0.59

تف

0.56

SignIn

0.55

 parseFloat

0.54

gpg

0.52

Activations Density 0.038%

references to specific academic affiliations and methods in research

No Comments

No Known Activations