INDEX

Explanations

references to keywords and their extraction in the context of programming or functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.72

apunov

-0.55

rrggbb

-0.52

 سكان

-0.51

oven

-0.51

❋

-0.50

 Outre

-0.49

 متعلقه

-0.49

Predecesor

-0.48

 StatefulWidget

-0.48

POSITIVE LOGITS

 propOrder

0.64

openqa

0.63

apimachinery

0.61

ArgumentParser

0.54

unsplash

0.53

illermo

0.52

CDATA

0.51

strptime

0.51

舺

0.50

ément

0.49

Activations Density 0.178%

references to keywords and their extraction in the context of programming or functionality

No Comments

No Known Activations