INDEX

Explanations

attends to tokens that appear in a specific format or context from tokens appearing later in the sequence

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

0:0.03

1:0.06

2:0.20

3:0.04

4:0.12

5:0.17

6:0.21

7:0.13

Negative Logits

Демографія

-0.48

RegressionTest

-0.42

EndProject

-0.41

AndroidJUnit

-0.40

 Италијани

-0.39

 للمعارف

-0.39

 ComVisible

-0.38

تفصیلات

-0.37

Abit

-0.36

 Uniti

-0.36

POSITIVE LOGITS

protoimpl

0.40

 invokingState

0.40

Hauptartikel

0.39

最快更新

0.36

expandindo

0.35

chau

0.34

ruf

0.32

UrlEncoded

0.31

PyErr

0.31

 initWithFrame

0.30

Activations Density 0.001%

attends to tokens that appear in a specific format or context from tokens appearing later in the sequence

No Comments

No Known Activations