INDEX

Explanations

references to photo credits and image attributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 raiſ

-0.98

 myſelf

-0.92

AddTagHelper

-0.86

 pleaſure

-0.86

 itſelf

-0.84

 faſt

-0.83

 تانيه

-0.81

ſelf

-0.79

 leaſt

-0.78

 ſtate

-0.78

POSITIVE LOGITS

 Images

0.59

 images

0.59

 image

0.58

image

0.58

photo

0.54

 publiques

0.53

 photo

0.53

tesy

0.53

 Image

0.51

 IMAGES

0.51

Activations Density 0.115%

references to photo credits and image attributions

No Comments

No Known Activations