INDEX

Explanations

attends to the token that follows posts from the same user across different sequences

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

0:0.13

1:0.24

2:0.14

3:0.06

4:0.12

5:0.05

6:0.05

7:0.16

Negative Logits

 myſelf

-0.55

 purpoſe

-0.52

 iſt

-0.50

 raiſ

-0.50

 Jefus

-0.47

ſelves

-0.47

 houſe

-0.47

 pleaſure

-0.47

 ſmall

-0.46

^(@)

-0.46

POSITIVE LOGITS

 وسلم

0.26

uis

0.26

 https

0.26

 isSet

0.25

er

0.25

the

0.24

servez

0.24

si

0.24

som

0.23

Activations Density 0.078%

attends to the token that follows posts from the same user across different sequences

No Comments

No Known Activations