INDEX

Explanations

the use of the word "between."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

čenje

-0.57

 complètes

-0.54

 orale

-0.54

 hvid

-0.53

Sho

-0.52

 vectorielles

-0.52

 Hawkeye

-0.52

 saker

-0.51

hol

-0.51

ho

-0.51

POSITIVE LOGITS

between

2.33

 Between

2.33

 between

2.32

Between

2.31

 BETWEEN

2.22

BETWEEN

2.18

 betwixt

2.04

 zwischen

1.89

 tussen

1.87

 mellom

1.76

Activations Density 0.098%

the use of the word "between."

No Comments

No Known Activations