INDEX

Explanations

references to masks or masking processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

]!='

-0.74

✨:

-0.72

 />";

-0.71

bereitung

-0.70

 pensato

-0.69

'].'

-0.68

 atof

-0.67

 domés

-0.66

 Sted

-0.65

 Eura

-0.65

POSITIVE LOGITS

 mask

2.59

 masks

2.48

 MASK

2.33

 Mask

2.32

Mask

2.32

mask

2.32

 Masks

2.20

masks

2.14

MASK

2.09

Masks

2.06

Activations Density 0.077%

references to masks or masking processes

No Comments

No Known Activations