INDEX

Explanations

instances of the word "watch" and its variations, indicating a focus on viewing or observing activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 gekomen

-0.46



-0.43

inai

-0.40

ergies

-0.39

GCM

-0.39

PPP

-0.38

 Freeport

-0.38

gemeinde

-0.38

er

-0.38

 Gari

-0.38

POSITIVE LOGITS

 Watch

1.39

 WATCH

1.34

 watch

1.34

 watching

1.31

Watch

1.26

watch

1.23

 watched

1.16

 Watching

1.16

 watches

1.13

WATCH

1.13

Activations Density 0.039%

instances of the word "watch" and its variations, indicating a focus on viewing or observing activities

No Comments

No Known Activations