INDEX

Explanations

attends to tool-related terms from action indicators or commands

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

0:0.17

1:0.19

2:0.22

3:0.11

4:0.08

5:0.04

6:0.06

7:0.10

Negative Logits

<?

-0.36

 >=",

-0.28

 pleaſure

-0.28

GRAFÍA

-0.26

RunWith

-0.26

 Greenberg

-0.25

PageIndex

-0.24

eux

-0.24

 makam

-0.24

 ↓,

-0.24

POSITIVE LOGITS

ніципалі

0.29

RDP

0.27

 ско

0.26

nodoc

0.25

 ddelweddau

0.25

libft

0.25

 Wallflower

0.24

cein

0.24

MigrationBuilder

0.24

ukone

0.24

Activations Density 0.096%

attends to tool-related terms from action indicators or commands

No Comments

No Known Activations