INDEX

Explanations

attends to certain property definitions from sequences that include the same type of property definitions or are related in 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

1:0.19

2:0.07

3:0.12

4:0.13

5:0.03

6:0.24

7:0.15

Negative Logits

^(@)

-0.89

 IBRARY

-0.83

 itſelf

-0.82

>\<^

-0.82

]--;

-0.81

NUMX

-0.81

 ―――――

-0.81

 myſelf

-0.81

)";

-0.81

 iſt

-0.80

POSITIVE LOGITS

↵↵

0.76

0.68

0.60

<eos>

0.57

0.56

0.55

0.50

Activations Density 0.051%

attends to certain property definitions from sequences that include the same type of property definitions or are related in context

No Comments

No Known Activations