INDEX

Explanations

patterns in structured data, specifically numeric values and coordinates

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

المناصب

-0.54

cythe

-0.53

covo

-0.51

 lộc

-0.50

 propósitos

-0.46

bodyParser

-0.46

odat

-0.46

 Knox

-0.45

 keputusan

-0.44

 Purdy

-0.44

POSITIVE LOGITS

 виправивши

0.80

FXMLLoader

0.79

HasForeignKey

0.74

FailureListener

0.74

URLException

0.73

MemoryWarning

0.70

ftagPool

0.69

 للمعارف

0.69

 BrowserModule

0.68

 nargin

0.68

Activations Density 0.781%

patterns in structured data, specifically numeric values and coordinates

No Comments

No Known Activations