INDEX

Explanations

attends to the category token from various instances where it is referenced later in the text

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.05

1:0.11

2:0.06

3:0.05

4:0.20

5:0.42

6:0.03

7:0.05

Negative Logits

ChildScrollView

-0.44

 समीक्षक

-0.40

LLocation

-0.40

CodeAttribute

-0.38

 themſelves

-0.38

 Signalez

-0.36

CodedInputStream

-0.35

 myſelf

-0.35

InvalidProtocol

-0.34

RenderAtEndOf

-0.34

POSITIVE LOGITS

GEBURTSDATUM

0.31

佗

0.26

 voie

0.26

<h2>

0.25

RetentionPolicy

0.25

 pinulongan

0.25

 Christo

0.25

ComponentScan

0.24

ッパ

0.24

IsUnicode

0.24

Activations Density 4.094%

attends to the category token from various instances where it is referenced later in the text

No Comments

No Known Activations