INDEX

Explanations

patterns in numerical data or coding structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

-0.54

-0.53

-0.51

of

-0.51

-0.50

ta

-0.49

POSITIVE LOGITS

IUrlHelper

1.12

 utafitiHapana

1.11

UserScript

1.02

InjectAttribute

1.00

estacks

0.99

İstinadlar

0.97

 autorytatywna

0.97

MethodManager

0.96

 linkovi

0.95

 EconPapers

0.95

Activations Density 0.398%

patterns in numerical data or coding structures

No Comments

No Known Activations