INDEX

Explanations

references to the concept of "pre" in various forms, indicating preparation or prior stages

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

 CiNii

-0.85

wisata

-0.84

 Wallflower

-0.84

 FishBase

-0.81

 Flows

-0.80

$}}

-0.80

zoek

-0.79

 LCCN

-0.78

bolista

-0.77

 دیکھیے

-0.77

POSITIVE LOGITS

Pre

2.43

Pre

2.36

pre

2.27

PRE

2.24

pre

2.17

PRE

2.10

 pré

1.80

 Pré

1.58

Pré

1.52

预

1.45

Activations Density 0.116%

references to the concept of "pre" in various forms, indicating preparation or prior stages

No Comments

No Known Activations