INDEX

Explanations

negative sentiments or critiques

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

 departament

-0.56

๋

-0.52

Palmar

-0.52

{?>

-0.49

"]),

-0.47

Ữ

-0.47

Gord

-0.46

 choisissez

-0.46

 joten

-0.45

 giovanni

-0.44

POSITIVE LOGITS

^(@)

0.75

DeleteBehavior

0.75

 ErrIntOverflow

0.73

 Мексичка

0.72

AsUp

0.70

 esternos

0.70

ỡng

0.69

 BoxFit

0.68

 beginnetje

0.67

DrawerToggle

0.66

Activations Density 1.292%

negative sentiments or critiques

No Comments

No Known Activations