INDEX

Explanations

attends to tokens that represent the prefix "Co" from various distinct tokens that appear later in the sequence

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.69

1:0.01

2:0.01

3:0.01

4:0.17

5:0.03

6:0.01

7:0.04

Negative Logits

 MatDialog

-0.31

 Xunit

-0.30

Portail

-0.28

ln

-0.28

 البي

-0.27

 arbres

-0.27

via

-0.27

 huiles

-0.27

 surla

-0.27

 huile

-0.27

POSITIVE LOGITS

thâu

0.44

зулта

0.41

κτηρισ

0.40

ględ

0.38

commodations

0.38

RuleContext

0.38

μως

0.38

Портал

0.37

Попис

0.36

المناصب

0.36

Activations Density 0.010%

attends to tokens that represent the prefix "Co" from various distinct tokens that appear later in the sequence

No Comments

No Known Activations