INDEX

Explanations

attends to properties related to types and parameters from specific data types indicated by square brackets

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

0:0.08

1:0.12

2:0.10

3:0.07

4:0.06

5:0.04

6:0.14

7:0.35

Negative Logits

gridx

-0.34

googleapis

-0.26

 Drummond

-0.26

Twas

-0.26

 rozgry

-0.25

↵↵

-0.25

ran

-0.25

ugno

-0.25

눠

-0.25

POSITIVE LOGITS

Slf

0.44

Hentet

0.42

//

0.42

URG

0.41

reuung

0.41

firi

0.41

abetes

0.40

Qua

0.40

 altrimenti

0.40

 néglig

0.39

Activations Density 0.061%

attends to properties related to types and parameters from specific data types indicated by square brackets

No Comments

No Known Activations