INDEX

Explanations

references to the word "these" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Kleidung

-0.67

 informaci

-0.63

 onPage

-0.57

Dul

-0.57

 gouttes

-0.56

 Öffentlichkeit

-0.56

addComponent

-0.56

dopodob

-0.56

Zil

-0.56

 abad

-0.55

POSITIVE LOGITS

 these

1.35

These

1.31

 These

1.24

 THESE

1.23

 theses

1.19

these

1.17

 Theſe

1.15

 Theses

1.14

 kinds

1.08

Эти

1.04

Activations Density 0.119%

references to the word "these" and its variations

No Comments

No Known Activations