INDEX

Explanations

phrases related to legal or regulatory standards

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

 Whilst

-0.73

Whilst

-0.68

ConstraintMaker

-0.66

 AspNetCore

-0.66

 Amongst

-0.63

DockStyle

-0.58

/-/

-0.57

batim

-0.57

ragona

-0.57

UnusedPrivate

-0.57

POSITIVE LOGITS

 Roskov

0.68

stdc

0.63

tvguidetime

0.62

 isinstance

0.59

OGND

0.59

soort

0.56

商品説明

0.55

webElementGuid

0.52

<bos>

0.52

VersionUID

0.51

Activations Density 0.064%

phrases related to legal or regulatory standards

No Comments

No Known Activations