INDEX

Explanations

attends to configuration-related tokens from tokens indicating file or stylistic elements

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

0:0.11

1:0.16

2:0.10

3:0.11

4:0.20

5:0.04

6:0.11

7:0.12

Negative Logits

 snippetHide

-0.67

RenderAtEndOf

-0.64

 '\\;'

-0.57

 typelib

-0.53

 NSCoder

-0.52

mybatisplus

-0.50

AddTagHelper

-0.50

 الحره

-0.49

 ISNI

-0.49

AndroidJUnit

-0.49

POSITIVE LOGITS

aka

0.32

anda

0.29

de

0.29

last

0.28

dia

0.28

л

0.28

ones

0.27

ma

0.27

holl

0.27

Activations Density 0.000%

attends to configuration-related tokens from tokens indicating file or stylistic elements

No Comments

No Known Activations