INDEX

Explanations

words and phrases related to modality and permission

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ImageContext

-0.78

 Majefty

-0.78

Efq

-0.74

 uſed

-0.71

 neceffary

-0.70

 poffible

-0.69

 iſt

-0.69

twimg

-0.68

 themſelves

-0.68

 nahilalakip

-0.67

POSITIVE LOGITS

zu

1.63

 auszu

0.94

te

0.83

å

0.79

Zu

0.78

Zu

0.76

 einzu

0.76

 ausz

0.75

 anzu

0.74

abz

0.70

Activations Density 0.064%

words and phrases related to modality and permission

No Comments

No Known Activations

words and phrases related to modality and permission

No Comments

No Known Activations