INDEX

Explanations

terms related to pixels in images

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 AssemblyCompany

-0.85

 Paglinawan

-0.80

 avoient

-0.79

 feroit

-0.78

 auroit

-0.76

parsedMessage

-0.75

 EconPapers

-0.75

 étoit

-0.72

richTextPanel

-0.71

 atve

-0.71

POSITIVE LOGITS

non

0.69

ют

0.68

ollectionView

0.61

 baseline

0.58

pixel

0.57

 tener

0.57

nem

0.56

por

0.54

 tiene

0.51

Pixel

0.51

Activations Density 0.151%

terms related to pixels in images

No Comments

No Known Activations