INDEX

Explanations

attends to specific tokens that represent particular entities or concepts from their associated counterparts

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

0:0.06

1:0.08

2:0.05

3:0.50

4:0.08

5:0.07

6:0.05

7:0.06

Negative Logits

errHandler

-0.47

AddTagHelper

-0.46

parseFrom

-0.45

noin

-0.44

zzleHttp

-0.42

});*/

-0.40

]))

-0.40

'])){

-0.40

 censi

-0.40

StoryboardSegue

-0.40

POSITIVE LOGITS

 LoggerFactory

0.38

 creciendo

0.37

kannya

0.35

jį

0.32

batore

0.31

ژه

0.31

 poils

0.30

 toalha

0.30

 tehd

0.30

ufig

0.30

Activations Density 0.480%

attends to specific tokens that represent particular entities or concepts from their associated counterparts

No Comments

No Known Activations