INDEX

Explanations

terms related to food and its properties or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Mares

-0.46

 Underground

-0.45

DIN

-0.44

 Humane

-0.43

Din

-0.43

Ramen

-0.43

 Burrow

-0.42

 Homeless

-0.42

 keten

-0.42

 chi̍t

-0.41

POSITIVE LOGITS

 fruit

1.35

 berry

1.17

fruit

1.16

 fruits

1.16

 berries

1.14

 Fruit

1.11

Fruit

1.09

 FRUIT

1.09

 Berries

1.02

 Fruits

1.01

Activations Density 0.239%

terms related to food and its properties or characteristics

No Comments

No Known Activations