INDEX

Explanations

attends to opening curly braces from token pairs involving a following token, regardless of context

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

1:0.05

2:0.05

3:0.06

4:0.06

5:0.03

6:0.09

7:0.58

Negative Logits

<eos>

-0.75

-0.74

↵↵

-0.74

-0.67

-0.66

-0.63

and

-0.63

POSITIVE LOGITS

 itſelf

1.29

 Theſe

1.27

 Monfieur

1.26

 myſelf

1.22

Efq

1.20

 ―――――

1.15

 Anſ

1.14

 Majefty

1.14

 doubtnut

1.13

ſelf

1.11

Activations Density 0.061%

attends to opening curly braces from token pairs involving a following token, regardless of context

No Comments

No Known Activations