INDEX

Explanations

attends to specific technical or professional terms from broader contextual terms

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

0:0.04

1:0.06

2:0.40

3:0.10

4:0.08

5:0.10

6:0.10

7:0.09

Negative Logits

GEBURTSDATUM

-0.34

–

-0.29

li

-0.29

cu

-0.28

gin

-0.27

ch

-0.26

vo

-0.26

cor

-0.26

rm

-0.25

POSITIVE LOGITS

 feroit

0.49

 auroit

0.45

 pouvoit

0.44

 étoit

0.43

ilhas

0.41

 étoient

0.40

 scattata

0.39

seamnă

0.39

amaño

0.38

SEGUIR

0.38

Activations Density 0.015%

attends to specific technical or professional terms from broader contextual terms

No Comments

No Known Activations