INDEX

Explanations

references to soup and related dishes

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

IntoConstraints

-0.90

contentLoaded

-0.78

 Monfieur

-0.77

 AssemblyCulture

-0.75

Efq

-0.75

Lähteet

-0.72

InteropServices

-0.69

 iſt

-0.66

 auffi

-0.66

 vPvB

-0.65

POSITIVE LOGITS

 soup

1.46

 Soup

1.40

 soups

1.34

soup

1.28

Soup

1.21

 noodles

1.07

 noodle

0.97

 Noodles

0.89

 Broth

0.89

 Noodle

0.88

Activations Density 0.200%

references to soup and related dishes

No Comments

No Known Activations