INDEX

Explanations

attends to tokens indicating purpose or reason from tokens referring to potential actions or outcomes

oai_attention-head · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k

Configuration

google/gemma-scope-2b-pt-att/layer_10/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.10.attn.hook_z

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.23

1:0.28

2:0.10

3:0.07

4:0.03

5:0.02

6:0.04

7:0.19

Negative Logits

 makeStyles

-0.30

 Patria

-0.26

didSet

-0.26

cado

-0.26

heide

-0.24

rostis

-0.24

offsetTop

-0.23

kuti

-0.23

 getSession

-0.23

doi

-0.23

POSITIVE LOGITS

 незавершена

0.43

Brainz

0.42

ValueStyle

0.41

Hauptartikel

0.41

 Normdatei

0.41

 nahilalakip

0.38

EDEFAULT

0.38

 gyhoeddwyd

0.36

 Wikimedijinoj

0.36

 MainAxisSize

0.36

Activations Density 0.106%

attends to tokens indicating purpose or reason from tokens referring to potential actions or outcomes

No Comments

No Known Activations