INDEX

Explanations

attends to schema location tokens from tokens specifying protocol or document type

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.15

1:0.10

2:0.12

3:0.07

4:0.07

5:0.09

6:0.06

7:0.29

Negative Logits

SharedDtor

-0.52

 tartalomajánló

-0.44

 BoxFit

-0.43

Personendaten

-0.43

 beginnetje

-0.42

 propOrder

-0.42

EDEFAULT

-0.41

GIVEREF

-0.40

 betweenstory

-0.40

 تضيفلها

-0.40

POSITIVE LOGITS

findpost

0.33

 strconv

0.25

 description

0.24

masta

0.24

}}_{\

0.24

\}\\

0.24

<strong>

0.23

 rumore

0.23

 measurement

0.23

ORP

0.23

Activations Density 0.001%

attends to schema location tokens from tokens specifying protocol or document type

No Comments

No Known Activations