INDEX

Explanations

attends to context-specific terms from corresponding tokens that represent categories or identifiers

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

1:0.14

2:0.15

3:0.08

4:0.10

5:0.04

6:0.16

7:0.14

Negative Logits

 MonoBehaviour

-0.35

RenderAtEndOf

-0.27

 externes

-0.26

endpush

-0.24

rijfs

-0.24

肇

-0.23

Linq

-0.23

aarrggbb

-0.23

 vernünf

-0.23

GEBURTSDATUM

-0.23

POSITIVE LOGITS

 USDA

0.30

 Radon

0.30

 препратки

0.30

Sma

0.29

 numberWith

0.29

Autoritní

0.29

apunov

0.29

 Minato

0.29

 Vard

0.29

AutoScaleMode

0.29

Activations Density 0.000%

attends to context-specific terms from corresponding tokens that represent categories or identifiers

No Comments

No Known Activations