INDEX

Explanations

actions related to pulling or drawing

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 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

Negative Logits

didSet

-0.65

istoitu

-0.63

Personensuche

-0.62

ритори

-0.62

ymce

-0.61

+#+#

-0.58

postIndex

-0.57

Архівовано

-0.57

 дописавши

-0.56

 médié

-0.56

POSITIVE LOGITS

 pull

1.00

Pull

0.91

 Pull

0.91

pull

0.90

 PULL

0.85

 draw

0.84

draw

0.82

 pulled

0.81

 pulling

0.81

 DRAW

0.79

Activations Density 0.269%

actions related to pulling or drawing

No Known Activations