INDEX

Explanations

references to earning or obtaining something, particularly in the context of advertising and endorsements

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

drawable

-0.71

-0.70

zerland

-0.69

anlage

-0.68

Sp

-0.67

igshid

-0.66

 Byrd

-0.66

 BoxDecoration

-0.65

 Rules

-0.65

POSITIVE LOGITS

FORUM

0.95

."</

0.94

 Bourne

0.93

 Mourinho

0.91

 '*',

0.90

 Voyager

0.89

 FORUM

0.88

TSM

0.88

 Journals

0.87

 JOURNAL

0.86

Activations Density 0.145%

references to earning or obtaining something, particularly in the context of advertising and endorsements

No Comments

No Known Activations