INDEX

Explanations

special formatting or syntax elements in the text

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

 themſelves

-0.95

 itſelf

-0.92

 Jefus

-0.91

 myſelf

-0.90

 ſeveral

-0.86

 Majefty

-0.83

 neceffary

-0.83

 fufficient

-0.81

 feveral

-0.79

felves

-0.79

POSITIVE LOGITS

writerow

0.63

 تانيه

0.62

GEBURTSDATUM

0.60

 DbSet

0.59

 RoutedEventArgs

0.58

të

0.57

يميديا

0.56

/\.

0.55

נ

0.53

 XCTest

0.53

Activations Density 0.070%

special formatting or syntax elements in the text

No Comments

No Known Activations