INDEX

Explanations

legal terminology and references related to procedure and classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 endfor

-0.61

Tembelea

-0.59

anthes

-0.56

 Италијани

-0.56

LLocation

-0.51

Démographie

-0.51

 iprot

-0.51

addPreferredGap

-0.50

 ddelweddau

-0.50



-0.49

POSITIVE LOGITS

two

3.43

 three

3.15

two

2.79

 four

2.72

 deux

2.64

three

2.54

 trois

2.48

 zwei

2.32

TWO

2.26

 drei

2.24

Activations Density 2.487%

legal terminology and references related to procedure and classification

No Comments

No Known Activations