INDEX

Explanations

attends to tokens associated with specific numerical values from related descriptive 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

0:0.07

1:0.08

2:0.12

3:0.15

4:0.11

5:0.13

6:0.20

7:0.10

Negative Logits

 myſelf

-0.95

 itſelf

-0.95

 Monfieur

-0.89

 ―――――

-0.87

ſelves

-0.85

 ་་

-0.83

 Anſ

-0.83

 Majefty

-0.82

 themſelves

-0.81

 doubtnut

-0.79

POSITIVE LOGITS

0.73

con

0.57

de

0.56

en

0.51

des

0.48

0.44

que

0.44

0.43

le

0.43

Mar

0.43

Activations Density 0.002%

attends to tokens associated with specific numerical values from related descriptive tokens

No Comments

No Known Activations