INDEX

Explanations

attends to the main function token from any following brace-enclosed argument list 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

0:0.12

1:0.15

2:0.12

3:0.16

4:0.12

5:0.05

6:0.12

7:0.13

Negative Logits

tvguidetime

-0.39

 doInBackground

-0.37

+#+#

-0.35

)";

-0.35

 EconPapers

-0.34

sizeCache

-0.32

`;

-0.32

 defStyle

-0.32

UseVisualStyle

-0.31

 مرئيه

-0.31

POSITIVE LOGITS

<eos>

0.29

 đoạn

0.28

SPJ

0.28

 colorWith

0.27

Zunanje

0.26

 Master

0.26

dragen

0.25

danno

0.24

 Nieren

0.24

 vétérina

0.24

Activations Density 0.030%

attends to the main function token from any following brace-enclosed argument list tokens

No Comments

No Known Activations

attends to the main function token from any following brace-enclosed argument list tokens

No Comments

No Known Activations