INDEX

Explanations

references to watching or viewing activities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+#

-0.69

ToolStrip

-0.54

området

-0.53

новниш

-0.53

 Mention

-0.51

Personensuche

-0.50

numerusform

-0.50

 mør

-0.50

 eorum

-0.50

 belirt

-0.50

POSITIVE LOGITS

 watch

1.12

 watching

0.91

 Watch

0.89

 watches

0.85

tvguidetime

0.84

watch

0.81

 WATCH

0.80

 Watching

0.78

Watch

0.76

 watched

0.73

Activations Density 0.076%

references to watching or viewing activities

No Comments

No Known Activations