INDEX

Explanations

numerical references and queries related to data or equations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

بوابة

-0.75

MessageTagHelper

-0.74

bor

-0.67

IndentedString

-0.66

BM

-0.66

 useNavigate

-0.65

Bor

-0.65

 Bere

-0.63

istic

-0.62

 lama

-0.61

POSITIVE LOGITS

1.29

1.20

1.17

 Quincy

1.16

CQ

1.15

 Quar

1.12

 Quay

1.08

 QUEST

1.07

 McQu

1.07

Activations Density 0.380%

numerical references and queries related to data or equations

No Comments

No Known Activations