INDEX

Explanations

attends to the token "v" from variable-related tokens

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

0:0.07

1:0.14

2:0.05

3:0.05

4:0.16

5:0.39

6:0.04

7:0.05

Negative Logits



-0.40

InjectAttribute

-0.34

Tse

-0.30

 colectiva

-0.29

|<\

-0.29

+:+

-0.28

OSP

-0.28

templateUrl

-0.28

 Trotz

-0.27

 Pilate

-0.27

POSITIVE LOGITS

IV

0.25

tax

0.24

Tax

0.24

 članak

0.24

logiques

0.23

logica

0.23

!*\

0.22

ciente

0.22

>");

0.22

 proprement

0.22

Activations Density 0.030%

attends to the token "v" from variable-related tokens

No Comments

No Known Activations