INDEX

Explanations

terms related to visual observation or effort

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

AsUp

-0.81

 Roskov

-0.76

 дописавши

-0.75

קישורים

-0.73

脚注の使い方

-0.70

 arşivlendi

-0.69

printStackTrace

-0.69

 nakalista

-0.68

 surla

-0.68

AccessorTable

-0.65

POSITIVE LOGITS

saw

2.79

 sees

2.37

 seen

2.37

saw

2.27

 seeing

2.12

Saw

2.11

Saw

2.02

sees

1.94

seen

1.91

 Sees

1.90

Activations Density 0.122%

terms related to visual observation or effort

No Comments

No Known Activations