INDEX

Explanations

references to images and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

essentiel

-0.56

excellents

-0.47

aucune

-0.47

few

-0.47

 voorwaarden

-0.45

rules

-0.44

habitude

-0.44

then

-0.44

intégr

-0.43

for

-0.43

POSITIVE LOGITS

 image

1.13

 Image

1.11

Image

1.07

image

1.04

 IMAGE

1.02

getImage

1.01

 getImage

0.98

IMAGE

0.92

 imagen

0.90

 images

0.87

Activations Density 0.055%

references to images and their attributes

No Comments

No Known Activations