INDEX

Explanations

attends to tokens related to library or resource identifiers from tokens that specify groups

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

1:0.03

2:0.07

3:0.33

4:0.14

5:0.09

6:0.17

7:0.11

Negative Logits

 myſelf

-0.60

etheless

-0.60

NUMX

-0.57

Efq

-0.56

 itſelf

-0.55

ſelf

-0.53

ſelves

-0.53

esterday

-0.53

 StatelessWidget

-0.51

ighed

-0.50

POSITIVE LOGITS

0.44

0.38

”

0.37

0.34

0.33

li

0.33

”.

0.33

Activations Density 0.001%

attends to tokens related to library or resource identifiers from tokens that specify groups

No Comments

No Known Activations