INDEX

Explanations

attends to verbs that indicate actions or processes from tokens indicating purpose or function

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

0:0.16

1:0.20

2:0.23

3:0.07

4:0.04

5:0.02

6:0.04

7:0.20

Negative Logits

 للمعارف

-0.33

tagHelperRunner

-0.32

 defaultstate

-0.30

 Indemnity

-0.29

InitVars

-0.28

ſelves

-0.28

IBarButtonItem

-0.28

 оригіналу

-0.28

 fVar

-0.28

KeySpec

-0.28

POSITIVE LOGITS

ueger

0.24

Portail

0.23

SharedDtor

0.23

 spørs

0.22

 kérd

0.21

setNext

0.21

sendStatus

0.20

WireFormat

0.20

rootDir

0.20

関連項目

0.20

Activations Density 0.225%

attends to verbs that indicate actions or processes from tokens indicating purpose or function

No Comments

No Known Activations