INDEX

Explanations

attends to various token patterns from numeric values and punctuation marks within relevant contexts

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

0:0.10

1:0.17

2:0.09

3:0.06

4:0.07

5:0.08

6:0.17

7:0.22

Negative Logits

-0.33

-0.26

الحياه

-0.26

strukturen

-0.25

Cas

-0.23

lla

-0.23

mical

-0.23

ynx

-0.23

POSITIVE LOGITS

AndEndTag

0.55

MessageOf

0.52

urlpatterns

0.50

 дописавши

0.49

rungsseite

0.44

 Мексичка

0.44

setVerticalGroup

0.41

+#+#

0.41

 GenerationType

0.41

 initComponents

0.40

Activations Density 0.001%

attends to various token patterns from numeric values and punctuation marks within relevant contexts

No Comments

No Known Activations