INDEX

Explanations

attends to tokens that specify particular designed systems from the broader context of tokens that outline general systems or categories

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

0:0.40

1:0.02

2:0.02

3:0.01

4:0.41

5:0.05

6:0.01

7:0.04

Negative Logits

DECREF

-0.59

istoitu

-0.54

 विश्वसनीयता

-0.50

ValueStyle

-0.48

ंदीखरीदारी

-0.48

 Roskov

-0.47

DebuggerNonUser

-0.47

-0.46

 Wicidata

-0.46

PYX

-0.46

POSITIVE LOGITS

ereich

0.36

 tantum

0.30

访

0.27

 directos

0.27

 NDEBUG

0.27

roga

0.26

 permita

0.26

 полу

0.26

 chargés

0.26

 addition

0.26

Activations Density 0.036%

attends to tokens that specify particular designed systems from the broader context of tokens that outline general systems or categories

No Comments

No Known Activations