INDEX

Explanations

attends to the token "mod" from various instances of the same token

oai_attention-head · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k

Configuration

google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

0:0.03

1:0.46

2:0.14

3:0.04

4:0.09

5:0.12

6:0.04

7:0.05

Negative Logits

van

-0.28

-0.27

reg

-0.26

mod

-0.24

mod

-0.24

 mode

-0.23

kil

-0.23

ú

-0.23

sk

-0.23

se

-0.23

POSITIVE LOGITS

 EconPapers

0.62

 Monfieur

0.54

 мәкал

0.46

 eenige

0.46

 Paglinawan

0.46

 themſelves

0.46

WithIOException

0.45

 varandra

0.45

 propOrder

0.45

ValueStyle

0.45

Activations Density 0.004%

attends to the token "mod" from various instances of the same token

No Comments

No Known Activations