INDEX

Explanations

attends to tokens associated with objects or categories from related tokens that are active or have an action

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

0:0.39

1:0.13

2:0.07

3:0.08

4:0.08

5:0.02

6:0.08

7:0.10

Negative Logits

is

-0.33

sig

-0.28

 πλα

-0.27

 করা

-0.27

is

-0.27

 present

-0.27

 république

-0.27

 Nieren

-0.26

mera

-0.26

POSITIVE LOGITS

TagMode

0.71

SequentialGroup

0.61

Tikang

0.57

ArgsConstructor

0.57

Datuak

0.54

Personensuche

0.52

ChildScrollView

0.52

enumii

0.52

новниш

0.51

ConstraintMaker

0.51

Activations Density 6.903%

attends to tokens associated with objects or categories from related tokens that are active or have an action

No Comments

No Known Activations