INDEX

Explanations

references to transactions or exchanges involving products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

makeText

-0.63

awtextra

-0.59

CloseOperation

-0.57

ArgumentParser

-0.55

 crossorigin

-0.53

unhofer

-0.51

bonucleic

-0.50

richTextPanel

-0.49

chádz

-0.48

,:]

-0.48

POSITIVE LOGITS

\{\\

0.69

 nakalista

0.61

 архивлан

0.57

 truffle

0.57

atshirt

0.57

CPtr

0.56

Хьажоргаш

0.56

 initComponents

0.56

 autorytatywna

0.55

NIS

0.55

Activations Density 1.239%

references to transactions or exchanges involving products or services

No Comments

No Known Activations