INDEX

Explanations

attends to tokens related to the honorable title from tokens that include personal names

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.01

1:0.04

2:0.08

3:0.47

4:0.05

5:0.04

6:0.14

7:0.12

Negative Logits

 itſelf

-0.71

Efq

-0.65

^(@)

-0.65

 myſelf

-0.60

 photolibrary

-0.58

 Roskov

-0.56

$_"

-0.56

ſelf

-0.56

 tfsi

-0.56

 ―――――

-0.55

POSITIVE LOGITS

0.37

<eos>

0.33

je

0.32

↵

0.31

Sp

0.30

fe

0.30

</h1>

0.30

</h4>

0.30

Activations Density 0.360%

attends to tokens related to the honorable title from tokens that include personal names

No Comments

No Known Activations