INDEX

Explanations

terms and phrases associated with specific names, titles, or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Viitteet

-0.73

 مشين

-0.68

aptation

-0.66

orthand

-0.66

hlander

-0.64

CELLANEOUS

-0.63

mistry

-0.62

ươi

-0.62

HomeAsUp

-0.60

 ProtoMessage

-0.59

POSITIVE LOGITS

0.74

ografija

0.60

QByteArray

0.57

Autoritní

0.56

̀nh

0.56

 UIAlert

0.55

 Autorizaciones

0.54

IVer

0.53

 scorso

0.53

Demografie

0.53

Activations Density 0.320%

terms and phrases associated with specific names, titles, or identifiers

No Comments

No Known Activations