INDEX

Explanations

attends to login-related tokens from subsequent authentication-related tokens

oai_attention-head · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k

Configuration

google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

0:0.09

1:0.24

2:0.14

3:0.08

4:0.18

5:0.08

6:0.06

7:0.09

Negative Logits

 ujednoznacz

-0.43

]='\

-0.37

ValueStyle

-0.36

 saites

-0.34

*/;

-0.33

Portale

-0.33

IntoConstraints

-0.33

 snippetHide

-0.33

AddTagHelper

-0.33

 FetchType

-0.32

POSITIVE LOGITS

we

0.26

he

0.22

last

0.22

 comigo

0.21

 consciência

0.21

we

0.21

most

0.21

 scientifiques

0.21

our

0.21

Activations Density 0.074%

attends to login-related tokens from subsequent authentication-related tokens

No Comments

No Known Activations