INDEX

Explanations

commands or references to "watch."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

/>";

-0.83

Abp

-0.81

])),

-0.78

}}],

-0.77

']),

-0.77

(;;)

-0.76

 للمعارف

-0.75

-0.73

cycline

-0.72

 Damien

-0.71

POSITIVE LOGITS

 watch

2.17

 Watch

2.16

 WATCH

2.07

watch

1.98

 watches

1.97

Watch

1.96

 Watches

1.84

WATCH

1.83

watches

1.78

 watched

1.68

Activations Density 0.103%

commands or references to "watch."

No Comments

No Known Activations