INDEX

Explanations

attends to tokens related to diplomatic titles from tokens related to geographic locations

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

0:0.12

1:0.19

2:0.17

3:0.07

4:0.10

5:0.04

6:0.10

7:0.18

Negative Logits

 surla

-0.40

Datuak

-0.40

ंदीखरीदारी

-0.36

tagena

-0.35

MMV

-0.30

Hauptartikel

-0.30

 typelib

-0.30

värr

-0.30

Tikang

-0.30

AILABLE

-0.30

POSITIVE LOGITS

RenderAtEndOf

0.20

 guste

0.20

 Nark

0.20

 IEnumerator

0.20

var

0.19

 onOptions

0.19

if

0.19

izr

0.19

let

0.19

Dim

0.19

Activations Density 0.063%

attends to tokens related to diplomatic titles from tokens related to geographic locations

No Comments

No Known Activations