INDEX

Explanations

references to pictures or visual media

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

images or visual representations

np_acts-logits-general · gemini-2.0-flash

visual depictions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 oreille

-0.66

brainly

-0.65

είς

-0.60

BeginContext

-0.58

olesale

-0.57

 rospy

-0.56

 defaultstate

-0.56

 MainAxisSize

-0.56

Према

-0.56

Abp

-0.55

POSITIVE LOGITS

 pictures

0.85

 picture

0.84

 Picture

0.74

 depicting

0.72

 showing

0.72

 images

0.71

 PICTURE

0.70

 pics

0.70

 imageNamed

0.69

picture

0.68

Activations Density 0.305%

references to pictures or visual media

images or visual representations

visual depictions

No Comments

No Known Activations