INDEX

Explanations

attends to unspecified tokens from tokens noted in the survey results

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

0:0.09

1:0.13

2:0.12

3:0.09

4:0.14

5:0.03

6:0.06

7:0.31

Negative Logits

ITUTE

-0.27

Configurer

-0.27

</b>

-0.26

ніципа

-0.26

PerformLayout

-0.24

ki

-0.24

bit

-0.23

 astore

-0.23

POSITIVE LOGITS

awtextra

0.56

OGND

0.51

/**

0.45

ArrowToggle

0.44

Geplaatst

0.43

aarrggbb

0.42

principalColumn

0.41

ReusableCell

0.40

 समीक्षाएं

0.40

ValueStyle

0.39

Activations Density 0.128%

attends to unspecified tokens from tokens noted in the survey results

No Comments

No Known Activations