INDEX

Explanations

attends to tokens connected with URLs or references from general statements or discussions about content

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

0:0.08

1:0.08

2:0.08

3:0.06

4:0.05

5:0.02

6:0.18

7:0.41

Negative Logits

}))

-0.38

titleMargin

-0.35

Filmography

-0.34

}));

-0.33

tvguidetime

-0.32

 мәкалә

-0.32

))->

-0.32

PerformLayout

-0.31

 pitié

-0.30

NameInMap

-0.30

POSITIVE LOGITS

ValueStyle

0.27

protoc

0.26

arest

0.26

mergeFrom

0.25

stretchr

0.24

 campaign

0.23

 Valer

0.23

 rules

0.23

ssil

0.22

 course

0.22

Activations Density 0.070%

attends to tokens connected with URLs or references from general statements or discussions about content

No Comments

No Known Activations