INDEX

Explanations

structures related to created attributes or metadata in a dataset

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

niosek

-0.70

DockStyle

-0.64

 SDLK

-0.63

KommentareTeilen

-0.61

 ويكيميديا

-0.61

 InputDecoration

-0.61

erencias

-0.58

 vPvB

-0.58

Hauptartikel

-0.58

XmlAccessType

-0.57

POSITIVE LOGITS

 date

1.41

 Date

1.30

date

1.27

Date

1.24

 dates

1.15

 timestamp

1.15

 DATE

1.15

 dated

1.07

DATE

1.04

 DateTime

1.01

Activations Density 0.482%

structures related to created attributes or metadata in a dataset

No Comments

No Known Activations