INDEX

Explanations

instances of the word "watch" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Abp

-0.89

 للمعارف

-0.84

])),

-0.77

 Damian

-0.75

}}],

-0.72

 Clough

-0.72

 Merr

-0.72

(;;)

-0.70

 Damien

-0.69

']),

-0.69

POSITIVE LOGITS

 watch

1.71

 WATCH

1.68

 Watch

1.65

 watches

1.57

 Watches

1.54

watches

1.50

watch

1.50

Watch

1.49

WATCH

1.48

 watched

1.47

Activations Density 0.048%

instances of the word "watch" and its variations in different contexts

No Comments

No Known Activations