INDEX

Explanations

attends to "pygame" from display-related tokens

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

0:0.04

1:0.06

2:0.09

3:0.11

4:0.08

5:0.33

6:0.13

7:0.13

Negative Logits

 myſelf

-1.83

 itſelf

-1.71

 Monfieur

-1.63

 ―――――

-1.59

 Majefty

-1.54

Efq

-1.54

 Jefus

-1.48

 purpoſe

-1.48

 doubtnut

-1.46

 ་་

-1.46

POSITIVE LOGITS

0.94

0.90

0.88

the

0.84

in

0.84

0.83

0.81

↵

0.80

Activations Density 0.003%

attends to "pygame" from display-related tokens

No Comments

No Known Activations