INDEX

Explanations

specific numerical information or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

hoon

-0.72

tvguidetime

-0.69

tidaknya

-0.68

fancy

-0.63

centration

-0.63

لكتر

-0.61

RenderAtEndOf

-0.59

Ծանոթ

-0.59

rogels

-0.59

 matri

-0.58

POSITIVE LOGITS

 fifteen

0.71

fif

0.69

Fifteen

0.68

AddField

0.68

Fif

0.67

Jop

0.67

 Fifteen

0.64

 best

0.62

 بيها

0.60

SuppressMessage

0.60

Activations Density 0.151%

specific numerical information or measurements

No Comments

No Known Activations