INDEX

Explanations

attends to "whole" from various later tokens indicating general concepts or entities

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

0:0.09

1:0.02

2:0.02

3:0.02

4:0.68

5:0.05

6:0.02

7:0.08

Negative Logits

 vastaan

-0.40

 aikana

-0.30

 ſmall

-0.30

 scatola

-0.30

 kleid

-0.29

soft

-0.29

 past

-0.29

 recent

-0.28

ⓧ

-0.28

 soft

-0.28

POSITIVE LOGITS

complexType

0.44

 stanovnika

0.43

 المعيارى

0.43

 MainAxisSize

0.42

äsident

0.41

 Lightboxes

0.41

 kasarigan

0.41

 AttributeSet

0.40

లాలు

0.40

bukkit

0.39

Activations Density 0.049%

attends to "whole" from various later tokens indicating general concepts or entities

No Comments

No Known Activations