INDEX

Explanations

programming syntax elements and variable assignments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Datuak

-0.73

 vampires

-0.70

 InputDecoration

-0.68

 <<<<<<<<<<<<<<

-0.67

 wireType

-0.66

ichia

-0.65

 ListTile

-0.63

المناصب

-0.63

jspx

-0.62

DrawerToggle

-0.61

POSITIVE LOGITS

 žiad

0.49

WaitGroup

0.47

IActionResult

0.46

 vence

0.44

SuppressLint

0.43

 žád

0.43

vad

0.42

penup

0.42

atiche

0.42

 quede

0.39

Activations Density 0.121%

programming syntax elements and variable assignments

No Comments

No Known Activations