INDEX

Explanations

attends to the words "bit" and "a" from various contexts, often followed by descriptive 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.22

1:0.20

2:0.21

3:0.04

4:0.04

5:0.02

6:0.04

7:0.20

Negative Logits

 typelib

-0.26

oredCriteria

-0.24

Tew

-0.24

psack

-0.23

ddar

-0.22

 समीक्षक

-0.22

ardians

-0.22

thoscope

-0.22

YNC

-0.22

edipus

-0.21

POSITIVE LOGITS

+#+#

0.35

ArgsConstructor

0.34

complexType

0.34

addContainerGap

0.33

存于互联网档案馆

0.30

 ويكيميديا

0.29

 فريبيس

0.28

μβρίου

0.28

 nargin

0.28

 combineReducers

0.28

Activations Density 0.213%

attends to the words "bit" and "a" from various contexts, often followed by descriptive tokens

No Comments

No Known Activations