INDEX

Explanations

attends to action-oriented tokens from subsequent response-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

0:0.09

1:0.10

2:0.09

3:0.14

4:0.12

5:0.07

6:0.19

7:0.17

Negative Logits

 Roskov

-0.36

()]

-0.34

UnsafeEnabled

-0.34

SuppressMessage

-0.27

!")

-0.27

()]);

-0.27

""}

-0.27

itri

-0.27

 comfor

-0.26

InjectAttribute

-0.26

POSITIVE LOGITS

Tikang

0.30

Vidite

0.29

partimento

0.28

licherweise

0.27

icestershire

0.26

ésult

0.26

HomeAsUpEnabled

0.25

davis

0.25

يكب

0.25

tonode

0.24

Activations Density 1.449%

attends to action-oriented tokens from subsequent response-related tokens

No Comments

No Known Activations