INDEX

Explanations

attends to the token "plt" from various plotting-related tokens

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

0:0.06

1:0.03

2:0.10

3:0.04

4:0.22

5:0.41

6:0.05

7:0.05

Negative Logits

 Monfieur

-0.72

 Anſ

-0.71

Efq

-0.70

 Reſ

-0.64

 ―――――

-0.63

 doubtnut

-0.63

 ainfi

-0.62

 Diſ

-0.62

 Houſe

-0.62

 ARXIV

-0.61

POSITIVE LOGITS

de

0.44

MigrationBuilder

0.42

0.41

”

0.40

“

0.40

↵

0.39

Rüyada

0.37

–

0.37

Activations Density 0.016%

attends to the token "plt" from various plotting-related tokens

No Comments

No Known Activations