INDEX

Explanations

references to pixels in imaging contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Kiz

-0.57

 Aene

-0.56

mazoo

-0.55

 Monfieur

-0.55

 XCTest

-0.54

Uff

-0.54

 suic

-0.53

computa

-0.53

 Eliz

-0.52

󠁮

-0.52

POSITIVE LOGITS

EDEFAULT

0.82

ArrowToggle

0.80

 <=",

0.80

 propOrder

0.71

Personendaten

0.71

:✨

0.70

 convertido

0.63

 يتيمه

0.63

 ProtoMessage

0.61

 PeEnEo

0.61

Activations Density 0.187%

references to pixels in imaging contexts

No Comments

No Known Activations